{ "data": { "category": { "area": "voice", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "description": "APIs that turn audio into text, streaming or in batch. Compared on accuracy across accents, noise, names and overlapping speakers, streaming latency, languages, diarisation and cost per audio minute.", "indexed": [ { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/2kw-mcp-server.json", "kind": "mcp", "name": "2kw.ai", "slug": "2kw-mcp-server", "url": "https://www.anchorterminal.com/tools/2kw-mcp-server" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/backengine-mcp.json", "kind": "mcp", "name": "backengine-mcp", "slug": "backengine-mcp", "url": "https://www.anchorterminal.com/tools/backengine-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/bigdata-mcp.json", "kind": "mcp", "name": "Bigdata.com", "slug": "bigdata-mcp", "url": "https://www.anchorterminal.com/tools/bigdata-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cleat.json", "kind": "mcp", "name": "Cleat", "slug": "cleat", "url": "https://www.anchorterminal.com/tools/cleat" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/clipy-mcp.json", "kind": "mcp", "name": "clipy.online MCP server", "slug": "clipy-mcp", "url": "https://www.anchorterminal.com/tools/clipy-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/dinglebear-cortex-rmcp.json", "kind": "mcp", "name": "Cortex RMCP", "slug": "dinglebear-cortex-rmcp", "url": "https://www.anchorterminal.com/tools/dinglebear-cortex-rmcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/crixin-voice.json", "kind": "mcp", "name": "Crixin Voice", "slug": "crixin-voice", "url": "https://www.anchorterminal.com/tools/crixin-voice" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/dialmcp.json", "kind": "mcp", "name": "DialMCP", "slug": "dialmcp", "url": "https://www.anchorterminal.com/tools/dialmcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gavelin-mcp.json", "kind": "mcp", "name": "Gavelin", "slug": "gavelin-mcp", "url": "https://www.anchorterminal.com/tools/gavelin-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/importly-mcp.json", "kind": "mcp", "name": "importly-mcp", "slug": "importly-mcp", "url": "https://www.anchorterminal.com/tools/importly-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/memoai-memo-ai.json", "kind": "mcp", "name": "Memo AI – meeting assistant", "slug": "memoai-memo-ai", "url": "https://www.anchorterminal.com/tools/memoai-memo-ai" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pepys-mcp.json", "kind": "mcp", "name": "pepys-mcp", "slug": "pepys-mcp", "url": "https://www.anchorterminal.com/tools/pepys-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/rephonic.json", "kind": "mcp", "name": "Rephonic", "slug": "rephonic", "url": "https://www.anchorterminal.com/tools/rephonic" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/soapnoteapi-mcp.json", "kind": "mcp", "name": "SOAPNoteAPI", "slug": "soapnoteapi-mcp", "url": "https://www.anchorterminal.com/tools/soapnoteapi-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scriptivox-transcription.json", "kind": "mcp", "name": "transcription", "slug": "scriptivox-transcription", "url": "https://www.anchorterminal.com/tools/scriptivox-transcription" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vexa.json", "kind": "mcp", "name": "Vexa", "slug": "vexa", "url": "https://www.anchorterminal.com/tools/vexa" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/yanlinglabs-video-extract-mcp.json", "kind": "mcp", "name": "Video Extract", "slug": "yanlinglabs-video-extract-mcp", "url": "https://www.anchorterminal.com/tools/yanlinglabs-video-extract-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/voxplo.json", "kind": "mcp", "name": "Voxplo", "slug": "voxplo", "url": "https://www.anchorterminal.com/tools/voxplo" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/getyoutubetranscript-youtube-transcript-and-youtube-search.json", "kind": "mcp", "name": "YouTube Transcript + YouTube Search MCP", "slug": "getyoutubetranscript-youtube-transcript-and-youtube-search", "url": "https://www.anchorterminal.com/tools/getyoutubetranscript-youtube-transcript-and-youtube-search" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/transcriptapi-youtube-transcript-and-youtube-search.json", "kind": "mcp", "name": "💯 YouTube Transcript + YouTube Search MCP for AI Agents", "slug": "transcriptapi-youtube-transcript-and-youtube-search", "url": "https://www.anchorterminal.com/tools/transcriptapi-youtube-transcript-and-youtube-search" } ], "indexedCount": 20, "json": "https://www.anchorterminal.com/categories/speech-to-text.json", "name": "Speech-to-text", "slug": "speech-to-text", "test": "The same audio set through every API, with accents, background noise, proper names and overlapping speakers. We measure word error rate on each slice, streaming latency to a final transcript, and cost per audio minute.", "title": "Speech-to-text APIs for AI agents", "toolCount": 10, "tools": [ "azure-speech-to-text", "amazon-transcribe", "deepgram-stt", "google-speech-to-text", "gladia-stt", "elevenlabs-scribe", "speechmatics-stt", "assemblyai-stt", "soniox-stt", "rev-ai-stt" ], "url": "https://www.anchorterminal.com/categories/speech-to-text" }, "tools": [ { "slug": "azure-speech-to-text", "name": "Azure AI Speech speech-to-text", "vendor": "Microsoft Azure", "vendorUrl": "https://azure.microsoft.com/en-us/products/ai-services/speech-to-text", "kind": "model", "category": "speech-to-text", "summary": "Azure's speech-to-text service for transcribing audio.", "url": "https://www.anchorterminal.com/tools/azure-speech-to-text", "markdownUrl": "https://www.anchorterminal.com/tools/azure-speech-to-text.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/azure-speech-to-text.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/azure-speech-to-text.json", "repo": "https://github.com/Azure-Samples/cognitive-services-speech-sdk", "license": "MIT (samples), SDK under Microsoft's own licence", "transports": [ "http" ], "remoteUrl": "https://eastus.api.cognitive.microsoft.com/speechtotext", "packages": [ { "registry": "pypi", "name": "azure-cognitiveservices-speech" }, { "registry": "npm", "name": "microsoft-cognitiveservices-speech-sdk" } ], "auth": "mixed", "authNotes": "`Ocp-Apim-Subscription-Key` header with a Speech resource key, or a Microsoft Entra ID bearer token (Microsoft's recommended keyless option). Endpoints are per region or per resource.", "pricing": "freemium", "pricingNotes": "Free F0 tier with 5 audio hours a month of real-time. Pay as you go in East US is $1 an hour real-time, $0.36 fast transcription, $0.18 batch, $1.20 custom real-time. Diarisation and continuous language ID in real time add $0.30 an hour each. MAI-Transcribe-2 is $0.10 an hour until 2026-12-31. Commitment tiers from $1,600 a month for 2,000 hours (https://azure.microsoft.com/en-us/pricing/details/speech/).", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Billing runs through a cloud account with a card or invoice.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3450, "npmWeekly": 475621, "pypiWeekly": 1032532, "asOf": "2026-09-30" }, "docsUrl": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-to-text", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "python", "typescript", "enterprise", "streaming", "batch", "async-jobs", "webhooks" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 77, "grade": "BB", "agentReady": true, "rank": 23, "ranked": true, "rankOf": 452, "categoryRank": 1, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 80, "payments": 20, "reliability": 90, "schema": 80, "security": 95, "transparency": 88 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Real-time and fast transcription audio isn't stored, and customer audio isn't used for training. MAI-Transcribe-2 is preview with no SLA, and its $0.10 promotional price ends on 2026-12-31.", "strengths": [ "Real-time and fast transcription audio isn't stored, and customer audio isn't used for training", "Fast transcription returns files up to 5 hours and 500 MB in one synchronous call", "Batch at $0.18 an hour, and a free F0 tier with 5 real-time hours a month", "429 guidance with a concrete backoff pattern of 1, 2, 4 and 4 minutes", "Keys or Entra ID tokens with role-based access" ], "weaknesses": [ "MAI-Transcribe-2 is preview with no SLA, and its $0.10 promotional price ends on 2026-12-31", "Real-time diarisation and language ID add $0.30 an hour each", "REST API v3.0 and the v3.2 previews were retired on 2026-03-31, and older samples still target them", "No llms.txt, and the pricing page needs JavaScript", "An Azure subscription needs a card, even for the F0 tier" ], "agentNotes": [ "Use fast transcription (`transcriptions:transcribe`) for files under 5 hours and 500 MB, and batch for bulk jobs", "Pin `api-version=2025-10-15`. v3.0 and the v3.2 previews are retired", "On a 429, back off 1, 2, 4 then 4 minutes. It usually means autoscaling, not a quota", "Set `timeToLive` on batch jobs or delete results, otherwise transcripts stay in Microsoft storage", "Don't budget on MAI-Transcribe-2 at $0.10 an hour after 2026-12-31" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 77 } ], "editorialScores": { "ergonomics": 75, "maintenance": 80, "payments": 20, "reliability": 90, "schema": 80, "security": 95, "transparency": 80 }, "provenanceScore": 95 }, "connect": { "install": "pip install azure-cognitiveservices-speech # or: npm i microsoft-cognitiveservices-speech-sdk", "http": "curl -X POST \"https://$AZURE_SPEECH_RESOURCE.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe?api-version=2025-10-15\" \\\n -H \"Ocp-Apim-Subscription-Key: $AZURE_SPEECH_KEY\" \\\n -F \"audio=@call.wav\" -F 'definition={\"locales\":[\"en-US\"]}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/azure-speech-to-text" }, "sameCompany": [ "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-text-to-speech", "microsoft-learn-mcp", "playwright-mcp", "azure-mcp", "azure-translator", "microsoft-graph-calendar" ], "area": "voice", "unitPrices": [ { "item": "Real-time standard", "unit": "audio-minute", "usd": 0.0167, "note": "$1 an hour, East US" }, { "item": "Fast transcription", "unit": "audio-minute", "usd": 0.006, "note": "$0.36 an hour" }, { "item": "Batch standard", "unit": "audio-minute", "usd": 0.003, "note": "$0.18 an hour" }, { "item": "MAI-Transcribe-2 (preview)", "unit": "audio-minute", "usd": 0.00167, "note": "$0.10 an hour, promotional until 2026-12-31" }, { "item": "Custom real-time", "unit": "audio-minute", "usd": 0.02, "note": "$1.20 an hour, plus endpoint hosting" }, { "item": "Real-time add-on (diarisation or language ID)", "unit": "audio-minute", "usd": 0.005, "note": "$0.30 an hour per feature" } ], "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "domainNote": "Endpoints are on speech.microsoft.com, api.cognitive.microsoft.com and cognitiveservices.azure.com. microsoft.com publishes a security.txt, but it passed its Expires date on 2026-09-23.", "endpointOnVendorDomain": true, "terms": "https://www.microsoft.com/licensing/terms/", "privacy": "https://privacy.microsoft.com/en-us/privacystatement", "statusPage": "https://azure.status.microsoft/en-us/status", "changelog": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/releasenotes", "securityTxt": "expired", "checked": "2026-09-30", "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/azure-speech-to-text.json", "live": { "slug": "azure-speech-to-text", "probe": { "target": "https://eastus.api.cognitive.microsoft.com/speechtotext", "method": "get", "lastAt": "2026-10-04T22:35:19.195646092Z", "lastOk": true, "lastStatus": 404, "lastMs": 335, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 333, "p95ms24h": 394, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://azure.status.microsoft/en-us/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:39:49.706276597Z" }, "versions": [ { "registry": "github", "name": "Azure-Samples/cognitive-services-speech-sdk", "version": "ingestion-v2.1.13", "released": "2026-07-10", "seenAt": "2026-10-04T16:21:35.861804644Z" }, { "registry": "npm", "name": "microsoft-cognitiveservices-speech-sdk", "version": "1.52.0", "seenAt": "2026-10-04T16:21:35.450134716Z" }, { "registry": "pypi", "name": "azure-cognitiveservices-speech", "version": "1.52.0", "released": "2026-09-28", "seenAt": "2026-10-04T16:21:35.259257344Z" } ], "githubStars": 3450, "npmWeekly": 508156, "pypiWeekly": 762825, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "expired", "expires": "2026-09-23T16:00:00.000Z", "checkedAt": "2026-10-04T15:16:01.36832038Z" }, "domain": { "domain": "microsoft.com", "registered": "1991-05-02", "source": "https://rdap.verisign.com/com/v1/domain/microsoft.com", "checkedAt": "2026-10-04T13:04:13.488857536Z" }, "pages": [ { "url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/releasenotes", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:45:30.876444067Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2950544cc00c" }, { "url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe", "kind": "deprecations", "status": 304, "checkedAt": "2026-10-04T15:45:28.887604282Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ebf9086dffd9" }, { "url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text", "kind": "deprecations", "status": 304, "checkedAt": "2026-10-04T15:45:32.859554147Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "fd2ed8814ecb" }, { "url": "https://azure.microsoft.com/en-us/pricing/details/speech/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:41:26.501161098Z", "changedAt": "2026-10-02T15:17:47.510097164Z", "fingerprint": "61d50da4e330" }, { "url": "https://privacy.microsoft.com/en-us/privacystatement", "kind": "privacy", "status": 200, "checkedAt": "2026-10-01T13:14:57.860748137Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "07484a06f35c" }, { "url": "https://www.microsoft.com/licensing/terms/", "kind": "terms", "status": 502, "checkedAt": "2026-10-01T13:17:52.720054167Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-04T22:35:19.195646092Z" } }, { "slug": "amazon-transcribe", "name": "Amazon Transcribe", "vendor": "Amazon Web Services", "vendorUrl": "https://aws.amazon.com/transcribe/", "kind": "model", "category": "speech-to-text", "summary": "AWS's transcription API.", "url": "https://www.anchorterminal.com/tools/amazon-transcribe", "markdownUrl": "https://www.anchorterminal.com/tools/amazon-transcribe.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/amazon-transcribe.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/amazon-transcribe.json", "repo": "https://github.com/awslabs/amazon-transcribe-streaming-sdk", "license": "Apache-2.0 (SDKs)", "transports": [ "http" ], "remoteUrl": "https://transcribe.us-east-1.amazonaws.com", "packages": [ { "registry": "pypi", "name": "amazon-transcribe" }, { "registry": "npm", "name": "@aws-sdk/client-transcribe" }, { "registry": "npm", "name": "@aws-sdk/client-transcribe-streaming" } ], "auth": "api-key", "authNotes": "AWS Signature Version 4 with IAM access keys or a role. Batch goes to `transcribe.\u003cregion\u003e.amazonaws.com`, streaming to `transcribestreaming.\u003cregion\u003e.amazonaws.com` (WebSocket needs a presigned URL).", "pricing": "usage", "pricingNotes": "US East is $0.006 a minute batch and $0.01 a minute streaming, billed per second with no minimum and up to two channels included. Diarisation, custom vocabularies and language ID are included. PII redaction adds $0.0024 a minute and custom language models $0.006. Accounts opened before 2025-07-15 get 60 free minutes a month for 12 months, newer accounts get Free Tier credits instead (https://aws.amazon.com/transcribe/pricing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Billing runs through a cloud account with a card or invoice.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 185, "npmWeekly": 505959, "pypiWeekly": 200552, "asOf": "2026-09-30" }, "docsUrl": "https://docs.aws.amazon.com/transcribe/latest/dg/what-is.html", "llmsTxt": "https://docs.aws.amazon.com/transcribe/latest/dg/llms.txt", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "tags": [ "hosted", "closed-source", "python", "typescript", "enterprise", "streaming", "batch", "async-jobs", "llms-txt", "card-required" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 73.6, "grade": "BB", "agentReady": true, "rank": 57, "ranked": true, "rankOf": 452, "categoryRank": 2, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 35, "payments": 20, "reliability": 95, "schema": 90, "security": 80, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "$0.006 a minute batch and $0.01 streaming in US East, with diarisation, custom vocabulary and language ID included. AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set.", "strengths": [ "$0.006 a minute batch and $0.01 streaming in US East, with diarisation, custom vocabulary and language ID included", "A reused `TranscriptionJobName` fails with `ConflictException`, so a retried submission can't create a second job", "IAM policies can limit a credential to single actions and resources", "Covered by the Amazon Machine Learning Language SLA", "No Transcribe events on the public health feeds for us-east-1, us-west-2 or eu-west-1 on 1 October 2026" ], "weaknesses": [ "AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set", "Batch input must sit in S3, and the WebSocket stream needs a presigned SigV4 URL", "No Transcribe document history entry since 2026-07-01", "Throttling returns `LimitExceededException` as a 400 with no Retry-After", "New accounts need a card, and the free minutes only apply to accounts opened before 2025-07-15" ], "agentNotes": [ "Give every job a unique `TranscriptionJobName`. A retry with the same name fails with `ConflictException` rather than starting a second job", "Batch is a job. Poll `GetTranscriptionJob` or listen on EventBridge, then fetch the transcript URI", "Set `OutputBucketName`, because job records are deleted after 90 days", "Back off on `LimitExceededException`. It arrives as a 400, not a 429", "Set the organisation's AI services opt-out policy before sending customer audio" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73.6 } ], "editorialScores": { "ergonomics": 80, "maintenance": 35, "payments": 20, "reliability": 95, "schema": 90, "security": 80, "transparency": 75 }, "provenanceScore": 95 }, "connect": { "install": "pip install boto3 amazon-transcribe # or: npm i @aws-sdk/client-transcribe", "http": "curl -X POST \"https://transcribe.us-east-1.amazonaws.com/\" \\\n --aws-sigv4 \"aws:amz:us-east-1:transcribe\" --user \"$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY\" \\\n -H \"X-Amz-Target: Transcribe.StartTranscriptionJob\" -H \"content-type: application/x-amz-json-1.1\" \\\n -d '{\"TranscriptionJobName\":\"call-001\",\"LanguageCode\":\"en-US\",\"Media\":{\"MediaFileUri\":\"s3://my-bucket/call.wav\"}}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/amazon-transcribe" }, "sameCompany": [ "amazon-bedrock-guardrails", "amazon-polly", "aws-secrets-manager", "aws-mcp-servers", "amazon-ses", "amazon-translate" ], "area": "voice", "unitPrices": [ { "item": "Batch", "unit": "audio-minute", "usd": 0.006, "note": "US East, per second" }, { "item": "Streaming", "unit": "audio-minute", "usd": 0.01, "note": "US East, per second" }, { "item": "PII redaction add-on", "unit": "audio-minute", "usd": 0.0024, "note": "first 250,000 minutes" }, { "item": "Custom language model add-on", "unit": "audio-minute", "usd": 0.006, "note": "first 250,000 minutes" } ], "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "amazon.com", "domainRegistered": "1994-11-01", "domainNote": "The endpoints are on amazonaws.com (registered 2005-08-18) and api.aws, both AWS domains. The security.txt on aws.amazon.com passed its Expires date on 2026-09-24.", "endpointOnVendorDomain": true, "terms": "https://aws.amazon.com/service-terms/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "https://health.aws.amazon.com/health/status", "changelog": "https://docs.aws.amazon.com/transcribe/latest/dg/doc-history.html", "securityTxt": "expired", "checked": "2026-09-30", "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/amazon-transcribe.json", "live": { "slug": "amazon-transcribe", "probe": { "target": "https://transcribe.us-east-1.amazonaws.com", "method": "get", "lastAt": "2026-10-04T22:35:18.596951225Z", "lastOk": true, "lastStatus": 404, "lastMs": 260, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 255, "p95ms24h": 314, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "versions": [ { "registry": "npm", "name": "@aws-sdk/client-transcribe", "version": "3.1146.0", "seenAt": "2026-10-04T16:20:14.407745351Z" }, { "registry": "npm", "name": "@aws-sdk/client-transcribe-streaming", "version": "3.1146.0", "seenAt": "2026-10-04T16:20:15.237150076Z" }, { "registry": "pypi", "name": "amazon-transcribe", "version": "0.6.4", "released": "2025-05-05", "seenAt": "2026-10-04T16:20:14.218395026Z" } ], "githubStars": 185, "npmWeekly": 609911, "pypiWeekly": 233186, "securityTxt": { "url": "https://amazon.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-04T15:15:49.458098289Z" }, "llmsTxt": { "url": "https://docs.aws.amazon.com/transcribe/latest/dg/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:18.885309232Z" }, "domain": { "domain": "amazon.com", "registered": "1994-11-01", "source": "https://rdap.verisign.com/com/v1/domain/amazon.com", "checkedAt": "2026-10-04T13:06:18.739682554Z" }, "pages": [ { "url": "https://docs.aws.amazon.com/transcribe/latest/dg/doc-history.html", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:43:22.418825271Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2b53ad2d121d" }, { "url": "https://aws.amazon.com/transcribe/pricing/", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:41:40.655188059Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9d86c82cdd96" } ], "updatedAt": "2026-10-04T22:35:18.596951225Z" } }, { "slug": "deepgram-stt", "name": "Deepgram Speech-to-Text (Nova-3, Flux)", "vendor": "Deepgram", "vendorUrl": "https://deepgram.com", "kind": "model", "category": "speech-to-text", "summary": "Deepgram's speech-to-text API for recorded audio and live streams, including turn detection for voice agents.", "url": "https://www.anchorterminal.com/tools/deepgram-stt", "markdownUrl": "https://www.anchorterminal.com/tools/deepgram-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepgram-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepgram-stt.json", "repo": "https://github.com/deepgram/deepgram-python-sdk", "license": "MIT (SDKs)", "transports": [ "http", "streamable-http", "stdio", "sse" ], "remoteUrl": "https://api.deepgram.com/v1", "packages": [ { "registry": "npm", "name": "@deepgram/sdk" }, { "registry": "pypi", "name": "deepgram-sdk" }, { "registry": "pypi", "name": "deepctl" } ], "auth": "api-key", "authNotes": "`Authorization: Token \u003ckey\u003e` header on REST and WebSocket calls. Short-lived JWTs (30-second TTL) from the token endpoint for browsers. The `dg` CLI MCP server uses `dg login` credentials or `DEEPGRAM_API_KEY`. The docs MCP needs no key.", "pricing": "usage", "pricingNotes": "$200 free credit with no card, then pay as you go, or Growth from $4,000 a year prepaid for up to 20 per cent off. Nova-3 pre-recorded $0.0043 a minute (multilingual $0.0052). Streaming Nova-3 is on a promotional $0.0048 a minute (regular $0.0077), multilingual $0.0058 (regular $0.0092). Flux English $0.0065 promotional (regular $0.0077), Flux Multilingual $0.0078. Streaming diarisation adds $0.0020 a minute, redaction $0.0020 and keyterm prompting $0.0013 (https://deepgram.com/pricing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 468, "npmWeekly": 1123798, "pypiWeekly": 805026, "asOf": "2026-09-30" }, "docsUrl": "https://developers.deepgram.com/docs/models-languages-overview", "llmsTxt": "https://developers.deepgram.com/llms.txt", "openapi": "https://developers.deepgram.com/openapi.json", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "tags": [ "hosted", "no-card", "closed-source", "python", "typescript", "openapi", "llms-txt", "mcp", "streaming", "batch", "webhooks", "enterprise", "self-hosted" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 70.6, "grade": "BB", "agentReady": true, "rank": 94, "ranked": true, "rankOf": 452, "categoryRank": 3, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 80, "payments": 40, "reliability": 65, "schema": 95, "security": 65, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Flux streams with model-level end-of-turn detection, so a voice agent needs no separate VAD. Training on audio is the default and the opt-out is a per-request flag.", "strengths": [ "Flux streams with model-level end-of-turn detection, so a voice agent needs no separate VAD", "Nova-3 pre-recorded at $0.0043 a minute with diarisation included", "OpenAPI and AsyncAPI files, an llms.txt and SDKs in six languages", "Keys can carry a role and an expiry date", "$200 free credit with no card" ], "weaknesses": [ "Training on audio is the default and the opt-out is a per-request flag", "Two incidents over 2 hours in July 2026, on Flux streaming and batch", "No SLA published for self-serve plans", "The privacy policy dates from October 2021 and doesn't mention the Model Improvement Program", "Streaming prices are promotional and may rise to the regular rate" ], "agentNotes": [ "Add `mip_opt_out=true` to every request that carries customer audio", "Use Flux (`flux-general-en`) on `/v2/listen` for live agents and Nova-3 for files", "Back off exponentially on 429. The concurrency limit is per project", "Pass `callback` for long files so the request doesn't hit the 10-minute processing timeout", "Mint keys with an expiry for short-lived jobs" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.6 } ], "editorialScores": { "ergonomics": 75, "maintenance": 80, "payments": 40, "reliability": 65, "schema": 95, "security": 65, "transparency": 60 }, "provenanceScore": 90 }, "connect": { "http": "curl -X POST \"https://api.deepgram.com/v1/listen?model=nova-3\u0026smart_format=true\u0026diarize=true\" \\\n -H \"Authorization: Token $DEEPGRAM_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"url\":\"https://dpgr.am/spacewalk.wav\"}'", "claudeCode": "claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp", "config": { "mcpServers": { "deepgram": { "args": [ "mcp" ], "command": "dg", "env": { "DEEPGRAM_API_KEY": "${DEEPGRAM_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/deepgram-stt" }, "sameCompany": [ "deepgram-tts", "deepgram-voice-agent" ], "area": "voice", "unitPrices": [ { "item": "Nova-3 pre-recorded", "unit": "audio-minute", "usd": 0.0043, "note": "pay as you go, diarisation included" }, { "item": "Nova-3 Multilingual pre-recorded", "unit": "audio-minute", "usd": 0.0052 }, { "item": "Nova-3 streaming", "unit": "audio-minute", "usd": 0.0048, "note": "promotional, regular $0.0077" }, { "item": "Nova-3 Multilingual streaming", "unit": "audio-minute", "usd": 0.0058, "note": "promotional, regular $0.0092" }, { "item": "Flux English streaming", "unit": "audio-minute", "usd": 0.0065, "note": "promotional, regular $0.0077" }, { "item": "Flux Multilingual streaming", "unit": "audio-minute", "usd": 0.0078 }, { "item": "Streaming diarisation add-on", "unit": "audio-minute", "usd": 0.002 } ], "provenance": { "legalEntity": "Deepgram, Inc.", "domain": "deepgram.com", "domainRegistered": "2016-01-28", "endpointOnVendorDomain": true, "terms": "https://deepgram.com/terms", "privacy": "https://deepgram.com/privacy", "statusPage": "https://status.deepgram.com", "changelog": "https://developers.deepgram.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "score": 90 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepgram-stt.json", "live": { "slug": "deepgram-stt", "probe": { "target": "https://api.deepgram.com/v1", "method": "get", "lastAt": "2026-10-04T22:35:21.883805881Z", "lastOk": true, "lastStatus": 404, "lastMs": 589, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 409, "p95ms24h": 576, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.deepgram.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:33:51.050807222Z" }, "versions": [ { "registry": "github", "name": "deepgram/deepgram-python-sdk", "version": "v7.12.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:25:14.377162819Z" }, { "registry": "npm", "name": "@deepgram/sdk", "version": "5.14.0", "seenAt": "2026-10-04T16:25:11.388177933Z" }, { "registry": "pypi", "name": "deepctl", "version": "0.3.1", "released": "2026-09-29", "seenAt": "2026-10-04T16:25:12.495057478Z" }, { "registry": "pypi", "name": "deepgram-sdk", "version": "7.12.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:25:12.291142743Z" } ], "githubStars": 468, "npmWeekly": 1147181, "pypiWeekly": 806541, "securityTxt": { "url": "https://deepgram.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:16:00.338324598Z" }, "llmsTxt": { "url": "https://developers.deepgram.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:29.891823062Z" }, "domain": { "domain": "deepgram.com", "registered": "2016-01-28", "source": "https://rdap.verisign.com/com/v1/domain/deepgram.com", "checkedAt": "2026-10-04T13:03:28.939824686Z" }, "pages": [ { "url": "https://developers.deepgram.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:42:47.246047138Z", "changedAt": "2026-10-03T15:30:58.169955011Z", "fingerprint": "906a55c83273" }, { "url": "https://deepgram.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:42:22.716687514Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9dc1aeac38eb" }, { "url": "https://deepgram.com/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:42:24.872646912Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "89846510fbe6" }, { "url": "https://deepgram.com/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-04T15:42:26.768797703Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7042d107fca1" } ], "updatedAt": "2026-10-04T22:35:21.883805881Z" } }, { "slug": "google-speech-to-text", "name": "Google Cloud Speech-to-Text", "vendor": "Google Cloud", "vendorUrl": "https://cloud.google.com/speech-to-text", "kind": "model", "category": "speech-to-text", "summary": "Google Cloud's transcription API.", "url": "https://www.anchorterminal.com/tools/google-speech-to-text", "markdownUrl": "https://www.anchorterminal.com/tools/google-speech-to-text.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/google-speech-to-text.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/google-speech-to-text.json", "repo": "https://github.com/googleapis/google-cloud-python/tree/main/packages/google-cloud-speech", "license": "Apache-2.0 (SDKs)", "transports": [ "http" ], "remoteUrl": "https://speech.googleapis.com/v2", "packages": [ { "registry": "pypi", "name": "google-cloud-speech" }, { "registry": "npm", "name": "@google-cloud/speech" } ], "auth": "oauth", "authNotes": "OAuth 2.0 bearer token from a service account or `gcloud` (Application Default Credentials) on a project with billing and the API turned on. Chirp 3 runs on the `us` and `eu` multi-region endpoints such as `us-speech.googleapis.com`.", "pricing": "freemium", "pricingNotes": "V2 standard recognition, which covers Chirp 3, is $0.016 a minute to 500,000 minutes a month, then $0.01, $0.008 and $0.004 past 2M. Dynamic batch is $0.003 a minute. Billed per second, per channel. V1 has 60 free minutes a month and charges $0.024 without data logging. Medical models $0.078 (https://cloud.google.com/speech-to-text/pricing).", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Billing runs through a cloud account with a card or invoice.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 713013, "pypiWeekly": 3703632, "asOf": "2026-09-30" }, "docsUrl": "https://docs.cloud.google.com/speech-to-text/docs", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "freemium", "closed-source", "python", "typescript", "enterprise", "streaming", "batch", "async-jobs", "card-required" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 70.4, "grade": "BB", "agentReady": true, "rank": 98, "ranked": true, "rankOf": 452, "categoryRank": 4, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 25, "payments": 20, "reliability": 85, "schema": 80, "security": 95, "transparency": 88 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Audio isn't stored or used for training unless the project opts in to data logging. No release note since 2025-11-13.", "strengths": [ "Audio isn't stored or used for training unless the project opts in to data logging", "No Speech-to-Text incident on the Google Cloud status page since 12 June 2025", "Dynamic batch at $0.003 a minute, and standard recognition tiers down to $0.004 past 2M minutes", "OAuth service accounts with IAM roles, and Cloud Audit Logs", "300 concurrent streams per region by default" ], "weaknesses": [ "No release note since 2025-11-13", "82 of the 111 Chirp 3 locales are preview", "Sync requests stop at 1 minute and streams at 5 minutes, and batch reads only from Cloud Storage", "No API keys in the documented V2 flow, and the free minutes need a billed project", "The quotas page doesn't say what error a breach returns or how to back off" ], "agentNotes": [ "Call Chirp 3 on the `us` or `eu` endpoint. It isn't listed for the `global` location", "Reopen streams before the 5-minute limit, or use `BatchRecognize` for recordings", "Downmix stereo unless you need channel labels, since each channel is billed", "Set dynamic batch on offline jobs to cut the price from $0.016 to $0.003 a minute", "Back off on `RESOURCE_EXHAUSTED`. The Speech docs don't give a retry interval" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.4 } ], "editorialScores": { "ergonomics": 70, "maintenance": 25, "payments": 20, "reliability": 85, "schema": 80, "security": 95, "transparency": 75 }, "provenanceScore": 100 }, "connect": { "install": "pip install google-cloud-speech # or: npm i @google-cloud/speech", "http": "curl -X POST \"https://us-speech.googleapis.com/v2/projects/$GOOGLE_CLOUD_PROJECT/locations/us/recognizers/_:recognize\" \\\n -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"content-type: application/json\" \\\n -d '{\"config\":{\"model\":\"chirp_3\",\"languageCodes\":[\"en-US\"],\"autoDecodingConfig\":{}},\"uri\":\"gs://cloud-samples-data/speech/brooklyn_bridge.flac\"}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/google-speech-to-text" }, "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-adk", "google-secret-manager", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "google-drive-api", "gemini-cli" ], "area": "voice", "unitPrices": [ { "item": "V2 standard recognition (Chirp 3)", "unit": "audio-minute", "usd": 0.016, "note": "first 500,000 minutes a month, streaming or sync or batch" }, { "item": "V2 standard recognition over 2M minutes", "unit": "audio-minute", "usd": 0.004 }, { "item": "V2 dynamic batch", "unit": "audio-minute", "usd": 0.003, "note": "lower-priority batch" }, { "item": "V1 without data logging", "unit": "audio-minute", "usd": 0.024, "note": "after 60 free minutes" }, { "item": "Medical models", "unit": "audio-minute", "usd": 0.078 } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997.", "endpointOnVendorDomain": true, "terms": "https://cloud.google.com/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://status.cloud.google.com", "changelog": "https://docs.cloud.google.com/speech-to-text/docs/release-notes", "securityTxt": "valid", "checked": "2026-09-30", "score": 100 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/google-speech-to-text.json", "live": { "slug": "google-speech-to-text", "probe": { "target": "https://speech.googleapis.com/v2", "method": "get", "lastAt": "2026-10-04T22:35:24.095368294Z", "lastOk": true, "lastStatus": 404, "lastMs": 45, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 44, "p95ms24h": 90, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.cloud.google.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-09-30T22:44:37.367865472Z" }, "versions": [ { "registry": "github", "name": "googleapis/google-cloud-python", "version": "sqlalchemy-bigquery-v1.17.3", "released": "2026-10-02", "seenAt": "2026-10-04T16:28:53.455824573Z" }, { "registry": "npm", "name": "@google-cloud/speech", "version": "8.1.1", "seenAt": "2026-10-04T16:28:52.627594401Z" }, { "registry": "pypi", "name": "google-cloud-speech", "version": "2.41.0", "released": "2026-10-01", "seenAt": "2026-10-04T16:28:52.433737787Z" } ], "githubStars": 5400, "npmWeekly": 786436, "pypiWeekly": 3475501, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-10-04T15:15:53.387118101Z" }, "domain": { "domain": "google.com", "registered": "1997-09-15", "source": "https://rdap.verisign.com/com/v1/domain/google.com", "checkedAt": "2026-10-04T13:05:50.737985829Z" }, "pages": [ { "url": "https://docs.cloud.google.com/speech-to-text/docs/release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:43:29.255732974Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "03f9dac9276b" }, { "url": "https://cloud.google.com/speech-to-text/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:41:59.781476607Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "c367763f8641" }, { "url": "https://cloud.google.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-01T13:11:34.992628421Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6798e0f4fb24" } ], "updatedAt": "2026-10-04T22:35:24.095368294Z" } }, { "slug": "gladia-stt", "name": "Gladia Speech-to-Text API + MCP", "vendor": "Gladia", "vendorUrl": "https://www.gladia.io", "kind": "model", "category": "speech-to-text", "summary": "Speech-to-text API for live and recorded audio, with multilingual transcription and code switching.", "url": "https://www.anchorterminal.com/tools/gladia-stt", "markdownUrl": "https://www.anchorterminal.com/tools/gladia-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gladia-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gladia-stt.json", "repo": "https://github.com/gladiaio/sdk", "license": "MIT (SDKs and MCP server)", "transports": [ "http", "stdio" ], "remoteUrl": "https://api.gladia.io/v2", "packages": [ { "registry": "npm", "name": "@gladiaio/sdk" }, { "registry": "pypi", "name": "gladiaio-sdk" }, { "registry": "npm", "name": "@gladiaio/mcp" } ], "auth": "api-key", "authNotes": "`x-gladia-key` header. Live sessions start with `POST /v2/live`, which returns a WebSocket URL. The MCP server reads `GLADIA_API_KEY` from the environment.", "pricing": "freemium", "pricingNotes": "Prepaid wallet. Starter is pay-as-you-go at $0.61 an hour async and $0.75 an hour real-time, with every add-on and language included. Growth, on an upfront commitment, goes as low as $0.20 async and $0.25 real-time. New accounts get a one-time €50 credit (https://www.gladia.io/pricing).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Billed to a funded account (checked 2026-09-30).", "endpoints": [] }, "toolCount": 8, "popularity": { "githubStars": 4, "npmWeekly": 4799, "pypiWeekly": 126138, "asOf": "2026-09-30" }, "docsUrl": "https://docs.gladia.io", "llmsTxt": "https://docs.gladia.io/llms.txt", "openapi": "https://api.gladia.io/openapi.json", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "freemium", "no-card", "mcp", "llms-txt", "openapi", "python", "typescript", "webhooks", "async-jobs", "streaming", "batch", "enterprise" ], "lastRelease": "2026-09-24", "graded": true, "anchor": { "graded": true, "score": 69.7, "grade": "B", "agentReady": false, "rank": 108, "ranked": true, "rankOf": 452, "categoryRank": 5, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 80, "payments": 40, "reliability": 60, "schema": 95, "security": 70, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "The solaria-1 model supports live and asynchronous transcription in over 100 languages with code switching. Starter pricing is $0.61 an hour for asynchronous transcription and $0.75 for real-time audio.", "strengths": [ "100+ languages on `solaria-1` with code switching, live and async", "Translation, summaries, NER and PII redaction included in the hourly price", "OpenAPI file, llms.txt, JavaScript and Python SDKs at 2.0.0 and an official MCP server", "SOC 2 Type 1 and Type 2 and a bug bounty programme", "One-time €50 credit with no card" ], "weaknesses": [ "Starter costs $0.61 an hour async and $0.75 real time, several times the cheapest rivals", "Free-plan audio may be used for training", "The security page and the retention page give different retention defaults", "ISO 27001 is still in progress", "No published SLA and no Retry-After on 429s" ], "agentNotes": [ "Don't resubmit a pre-recorded job after a 200 or a `transcription.created` webhook. It's already queued", "Pick `solaria-3` only for async EN, FR, DE, ES or IT audio. Anything live or multilingual needs `solaria-1`", "A 429 means the concurrency limit, 3 async and 1 live on the free plan. Wait for a running job to finish", "Upgrade off the free plan before sending sensitive audio", "Split files over 135 minutes or 1,000 MB" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.7 } ], "editorialScores": { "ergonomics": 75, "maintenance": 80, "payments": 40, "reliability": 60, "schema": 95, "security": 70, "transparency": 50 }, "provenanceScore": 82 }, "connect": { "http": "curl https://api.gladia.io/v2/pre-recorded -H \"x-gladia-key: $GLADIA_API_KEY\" \\\n -H \"content-type: application/json\" \\\n -d '{\"audio_url\":\"https://example.com/audio.mp3\",\"diarization\":true}'", "claudeCode": "claude mcp add gladia --env GLADIA_API_KEY=$GLADIA_API_KEY -- npx -y @gladiaio/mcp", "config": { "mcpServers": { "gladia": { "args": [ "-y", "@gladiaio/mcp" ], "command": "npx", "env": { "GLADIA_API_KEY": "${GLADIA_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/gladia-stt" }, "area": "voice", "unitPrices": [ { "item": "Starter async", "unit": "audio-minute", "usd": 0.0102, "note": "published as $0.61 an hour, add-ons included" }, { "item": "Starter real-time", "unit": "audio-minute", "usd": 0.0125, "note": "published as $0.75 an hour, add-ons included" }, { "item": "Growth async", "unit": "audio-minute", "usd": 0.0033, "note": "from $0.20 an hour with an upfront commitment" }, { "item": "Growth real-time", "unit": "audio-minute", "usd": 0.0042, "note": "from $0.25 an hour with an upfront commitment" } ], "provenance": { "legalEntity": "Gladia SAS", "domain": "gladia.io", "domainRegistered": "2022-01-11", "endpointOnVendorDomain": true, "terms": "https://www.gladia.io/terms-conditions", "privacy": "https://www.gladia.io/privacy-notice", "statusPage": "https://status.gladia.io", "changelog": "https://www.gladia.io/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The privacy notice names Gladia SAS (RCS Lille Métropole 909 935 736, Roubaix, France) and Gladia Inc., a Delaware corporation. Separate terms exist for each at https://www.gladia.io/terms-conditions-gladia-inc" ], "score": 82 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gladia-stt.json", "live": { "slug": "gladia-stt", "probe": { "target": "https://api.gladia.io/v2", "method": "get", "lastAt": "2026-10-04T22:35:23.848697723Z", "lastOk": true, "lastStatus": 404, "lastMs": 347, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 411, "p95ms24h": 750, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.gladia.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:33:56.102634317Z" }, "versions": [ { "registry": "npm", "name": "@gladiaio/mcp", "version": "0.1.1", "seenAt": "2026-10-04T16:28:09.051373117Z" }, { "registry": "npm", "name": "@gladiaio/sdk", "version": "2.1.0", "seenAt": "2026-10-04T16:28:07.964822187Z" }, { "registry": "pypi", "name": "gladiaio-sdk", "version": "2.1.0", "released": "2026-09-18", "seenAt": "2026-10-04T16:28:08.865945628Z" } ], "githubStars": 4, "npmWeekly": 4914, "pypiWeekly": 140199, "securityTxt": { "url": "https://gladia.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:43.816809218Z" }, "llmsTxt": { "url": "https://docs.gladia.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:48.420893226Z" }, "domain": { "domain": "gladia.io", "checkedAt": "2026-10-04T13:09:15.943536897Z" }, "pages": [ { "url": "https://www.gladia.io/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:50:30.16447742Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "fd6e6ef5a4f5" }, { "url": "https://www.gladia.io/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:50:32.208809922Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "eab6d997a7d1" }, { "url": "https://www.gladia.io/privacy-notice", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:50:34.177843509Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "c8289a93b7ab" }, { "url": "https://www.gladia.io/terms-conditions", "kind": "terms", "status": 304, "checkedAt": "2026-10-04T15:50:36.18023534Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3fb9c6a0af20" } ], "updatedAt": "2026-10-04T22:35:23.848697723Z" } }, { "slug": "elevenlabs-scribe", "name": "ElevenLabs Scribe Speech to Text API", "vendor": "ElevenLabs", "vendorUrl": "https://elevenlabs.io", "kind": "model", "category": "speech-to-text", "summary": "ElevenLabs' speech-to-text service for audio transcription.", "url": "https://www.anchorterminal.com/tools/elevenlabs-scribe", "markdownUrl": "https://www.anchorterminal.com/tools/elevenlabs-scribe.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/elevenlabs-scribe.json", "repo": "https://github.com/elevenlabs/elevenlabs-python", "license": "MIT (SDKs)", "transports": [ "http", "stdio" ], "remoteUrl": "https://api.elevenlabs.io/v1", "packages": [ { "registry": "npm", "name": "@elevenlabs/elevenlabs-js" }, { "registry": "pypi", "name": "elevenlabs" }, { "registry": "pypi", "name": "elevenlabs-mcp" } ], "auth": "api-key", "authNotes": "`xi-api-key` header on `POST /v1/speech-to-text` and the realtime WebSocket. The hosted MCP server doesn't expose transcription. Only the deprecated local `elevenlabs-mcp` server has a `speech_to_text` tool.", "pricing": "freemium", "pricingNotes": "Scribe v2 and Scribe v2 Medical cost $0.22 an hour of audio, Scribe v2 Realtime $0.39 an hour. Entity detection adds $0.07 an hour and keyterm prompting $0.05 an hour. Silence counts. Free includes about 4.5 hours of batch audio a month, Starter $6 27 hours, Creator $22 100 hours, Pro $99 450 hours, Scale $299 1,359 hours and Business $990 4,500 hours (https://elevenlabs.io/pricing/api).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3122, "npmWeekly": 1063065, "pypiWeekly": 2223099, "asOf": "2026-09-30" }, "docsUrl": "https://elevenlabs.io/docs/overview/capabilities/speech-to-text", "llmsTxt": "https://elevenlabs.io/docs/llms.txt", "openapi": "https://api.elevenlabs.io/openapi.json", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "python", "typescript", "openapi", "llms-txt", "streaming", "batch", "webhooks", "async-jobs", "enterprise" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 69, "grade": "B", "agentReady": false, "rank": 117, "ranked": true, "rankOf": 452, "categoryRank": 6, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 75, "payments": 40, "reliability": 70, "schema": 95, "security": 55, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "$0.22 an hour for batch with 90+ languages and diarisation to 32 speakers. Audio may be used for training unless the account opts out, and the opt-out isn't retroactive.", "strengths": [ "$0.22 an hour for batch with 90+ languages and diarisation to 32 speakers", "Keys restricted by endpoint, capped by credits and set to expire", "429 codes named in the error reference with exponential backoff guidance", "Files up to 3 GB and 10 hours, or a `source_url`", "OpenAPI file and an llms.txt with Markdown pages" ], "weaknesses": [ "Audio may be used for training unless the account opts out, and the opt-out isn't retroactive", "Speech-to-text data is retained by default, and zero retention needs Enterprise", "STT request failures for 94 minutes on 29 September 2026, plus latency incidents on 26 August, 4 September and 28 September", "Realtime costs $0.39 an hour, nearly double batch", "No self-serve SLA found" ], "agentNotes": [ "Create a key restricted to speech-to-text with a credit quota and an expiry", "Use `source_url` for hosted files instead of downloading and re-uploading", "Set `webhook=true` for long files so the call doesn't block", "Back off exponentially on any of the three 429 codes", "Opt out under Data use before sending customer audio. It only covers later uploads" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69 } ], "editorialScores": { "ergonomics": 75, "maintenance": 75, "payments": 40, "reliability": 70, "schema": 95, "security": 55, "transparency": 50 }, "provenanceScore": 92 }, "connect": { "http": "curl -X POST https://api.elevenlabs.io/v1/speech-to-text -H \"xi-api-key: $ELEVENLABS_API_KEY\" \\\n -F model_id=scribe_v2 -F diarize=true -F file=@call.mp3", "config": { "mcpServers": { "elevenlabs": { "args": [ "elevenlabs-mcp" ], "command": "uvx", "env": { "ELEVENLABS_API_KEY": "${ELEVENLABS_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/elevenlabs-scribe" }, "sameCompany": [ "elevenlabs-music", "elevenlabs-tts", "elevenlabs-agents", "elevenlabs-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "Scribe v2 batch", "unit": "audio-minute", "usd": 0.0037, "note": "published as $0.22 an hour, also Scribe v2 Medical" }, { "item": "Scribe v2 Realtime", "unit": "audio-minute", "usd": 0.0065, "note": "published as $0.39 an hour" }, { "item": "Entity detection add-on", "unit": "audio-minute", "usd": 0.0012, "note": "published as $0.07 an hour" }, { "item": "Keyterm prompting add-on", "unit": "audio-minute", "usd": 0.0008, "note": "published as $0.05 an hour" } ], "provenance": { "legalEntity": "Eleven Labs Inc.", "domain": "elevenlabs.io", "domainRegistered": "2021-12-15", "endpointOnVendorDomain": true, "terms": "https://elevenlabs.io/terms-of-use", "privacy": "https://elevenlabs.io/privacy-policy", "statusPage": "https://status.elevenlabs.io", "changelog": "https://elevenlabs.io/docs/changelog", "securityTxt": "valid", "checked": "2026-09-30", "score": 92 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/elevenlabs-scribe.json", "live": { "slug": "elevenlabs-scribe", "probe": { "target": "https://api.elevenlabs.io/v1", "method": "get", "lastAt": "2026-10-04T22:35:22.783891528Z", "lastOk": true, "lastStatus": 404, "lastMs": 112, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 119, "p95ms24h": 184, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.elevenlabs.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:33:52.01957055Z" }, "versions": [ { "registry": "github", "name": "elevenlabs/elevenlabs-python", "version": "v2.70.0", "released": "2026-09-28", "seenAt": "2026-10-04T16:26:17.25929198Z" }, { "registry": "npm", "name": "@elevenlabs/elevenlabs-js", "version": "2.70.0", "seenAt": "2026-10-04T16:26:14.91095365Z" }, { "registry": "pypi", "name": "elevenlabs", "version": "2.70.0", "released": "2026-09-28", "seenAt": "2026-10-04T16:26:15.174074453Z" }, { "registry": "pypi", "name": "elevenlabs-mcp", "version": "0.12.2", "released": "2026-08-04", "seenAt": "2026-10-04T16:26:15.283719447Z" } ], "githubStars": 3129, "npmWeekly": 1135260, "pypiWeekly": 2247596, "securityTxt": { "url": "https://elevenlabs.io/.well-known/security.txt", "state": "valid", "expires": "2027-03-01T00:00:00.000Z", "checkedAt": "2026-10-04T15:15:51.968224287Z" }, "llmsTxt": { "url": "https://elevenlabs.io/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:47.706081321Z" }, "domain": { "domain": "elevenlabs.io", "checkedAt": "2026-10-04T13:07:28.958673807Z" }, "updatedAt": "2026-10-04T22:35:22.783891528Z" } }, { "slug": "speechmatics-stt", "name": "Speechmatics Speech-to-Text", "vendor": "Speechmatics", "vendorUrl": "https://www.speechmatics.com", "kind": "model", "category": "speech-to-text", "summary": "Speechmatics' APIs for batch and real-time transcription, including speaker-attributed turns for voice agents.", "url": "https://www.anchorterminal.com/tools/speechmatics-stt", "markdownUrl": "https://www.anchorterminal.com/tools/speechmatics-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/speechmatics-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/speechmatics-stt.json", "repo": "https://github.com/speechmatics/speechmatics-python-sdk", "license": "MIT (SDKs)", "transports": [ "http" ], "remoteUrl": "https://eu1.asr.api.speechmatics.com/v2", "packages": [ { "registry": "npm", "name": "@speechmatics/batch-client" }, { "registry": "npm", "name": "@speechmatics/real-time-client" }, { "registry": "pypi", "name": "speechmatics-batch" }, { "registry": "pypi", "name": "speechmatics-rt" } ], "auth": "api-key", "authNotes": "API key as a Bearer token. Short-lived JWTs for browser and realtime clients, passed as `?jwt=` on the WebSocket URL. A separate management token covers project and key administration.", "pricing": "usage", "pricingNotes": "$100 free credit with no card, then pay as you go per hour of audio, billed to the second. Batch Melia 1 $0.13, Batch Standard $0.24, Batch Enhanced $0.40, Realtime Standard $0.24, Realtime Enhanced $0.43, Linden 1 (Agent STT) $0.16 (was $0.21). Translation adds $0.65 an hour. 20 per cent off usage over 500 hours a month per model, and 33 per cent off if you opt in to model training (https://www.speechmatics.com/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 20, "npmWeekly": 58050, "pypiWeekly": 48085, "asOf": "2026-09-30" }, "docsUrl": "https://docs.speechmatics.com", "llmsTxt": "https://docs.speechmatics.com/llms.txt", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "no-card", "closed-source", "python", "typescript", "llms-txt", "streaming", "batch", "webhooks", "async-jobs", "enterprise", "self-hosted" ], "lastRelease": "2026-09-22", "graded": true, "anchor": { "graded": true, "score": 67.3, "grade": "B", "agentReady": false, "rank": 145, "ranked": true, "rankOf": 452, "categoryRank": 7, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 75, "payments": 40, "reliability": 70, "schema": 65, "security": 65, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Training is opt-in and real-time audio is not stored. Enhanced transcription costs $0.40 to $0.43 an hour.", "strengths": [ "Training is opt-in only, and realtime audio isn't stored", "ISO/IEC 27001:2022 and SOC 2 Type II", "Transcripts fetched as plain text, JSON or SRT", "Ten dated changelog entries in September 2026", "$100 credit with no card" ], "weaknesses": [ "Enhanced costs $0.40 to $0.43 an hour, above most rivals", "No OpenAPI or AsyncAPI file linked from the docs", "429s carry a reason but no Retry-After or backoff guidance", "Realtime JWTs travel in the WebSocket URL", "Free plan allows 2 realtime sessions" ], "agentNotes": [ "Set `\"model\": \"enhanced\"` explicitly. The default is `standard`", "Use notifications instead of polling. Polling waits 5 seconds by default since the 23 September 2026 change, and `wait=0` turns that off", "Fetch batch transcripts within 7 days. After that the API returns 404 `expired`", "Pass a `fetch_data` URL for files over 1 GB", "Use `/v2/agent` with `linden-1` for live agents instead of the plain realtime path" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.3 } ], "editorialScores": { "ergonomics": 80, "maintenance": 75, "payments": 40, "reliability": 70, "schema": 65, "security": 65, "transparency": 65 }, "provenanceScore": 90 }, "connect": { "http": "curl -X POST https://eu1.asr.api.speechmatics.com/v2/jobs/ -H \"Authorization: Bearer $SPEECHMATICS_API_KEY\" \\\n -F data_file=@call.wav \\\n -F config='{\"type\":\"transcription\",\"transcription_config\":{\"language\":\"en\",\"model\":\"enhanced\",\"diarization\":\"speaker\"}}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/speechmatics-stt" }, "area": "voice", "unitPrices": [ { "item": "Batch Melia 1", "unit": "audio-minute", "usd": 0.0022, "note": "published as $0.13 an hour" }, { "item": "Batch Standard", "unit": "audio-minute", "usd": 0.004, "note": "published as $0.24 an hour" }, { "item": "Batch Enhanced", "unit": "audio-minute", "usd": 0.0067, "note": "published as $0.40 an hour" }, { "item": "Realtime Standard", "unit": "audio-minute", "usd": 0.004, "note": "published as $0.24 an hour" }, { "item": "Realtime Enhanced", "unit": "audio-minute", "usd": 0.0072, "note": "published as $0.43 an hour" }, { "item": "Linden 1 Agent STT", "unit": "audio-minute", "usd": 0.0027, "note": "published as $0.16 an hour, reduced from $0.21" }, { "item": "Translation add-on", "unit": "audio-minute", "usd": 0.0108, "note": "published as $0.65 an hour" } ], "provenance": { "legalEntity": "Cantab Research Ltd", "domain": "speechmatics.com", "domainRegistered": "2006-05-10", "endpointOnVendorDomain": true, "terms": "https://www.speechmatics.com/legal/terms-of-service", "privacy": "https://www.speechmatics.com/legal/privacy-policy", "statusPage": "https://status.speechmatics.com", "changelog": "https://speechmatics.featurebase.app/en/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Trades as Speechmatics, company number 05697423 in England and Wales. US customers contract with Speechmatics (USA) Inc., a Delaware company" ], "score": 90 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/speechmatics-stt.json", "live": { "slug": "speechmatics-stt", "probe": { "target": "https://eu1.asr.api.speechmatics.com/v2", "method": "get", "lastAt": "2026-10-04T22:35:31.760482402Z", "lastOk": true, "lastStatus": 200, "lastMs": 66, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 69, "p95ms24h": 167, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.speechmatics.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:34:09.110198473Z" }, "versions": [ { "registry": "github", "name": "speechmatics/speechmatics-python-sdk", "version": "agent-stt/v0.2.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:40:31.792271239Z" }, { "registry": "npm", "name": "@speechmatics/batch-client", "version": "5.4.2", "seenAt": "2026-10-04T16:40:27.482066747Z" }, { "registry": "npm", "name": "@speechmatics/real-time-client", "version": "8.5.1", "seenAt": "2026-10-04T16:40:28.316137146Z" }, { "registry": "pypi", "name": "speechmatics-batch", "version": "1.1.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:40:29.706091183Z" }, { "registry": "pypi", "name": "speechmatics-rt", "version": "1.2.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:40:29.900002888Z" } ], "githubStars": 20, "npmWeekly": 43504, "pypiWeekly": 12463, "securityTxt": { "url": "https://speechmatics.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:16:00.14853587Z" }, "llmsTxt": { "url": "https://docs.speechmatics.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:15.724971305Z" }, "domain": { "domain": "speechmatics.com", "registered": "2006-05-10", "source": "https://rdap.verisign.com/com/v1/domain/speechmatics.com", "checkedAt": "2026-10-04T13:05:04.524690122Z" }, "pages": [ { "url": "https://speechmatics.featurebase.app/en/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:48:01.803582196Z", "changedAt": "2026-10-02T15:24:13.144056184Z", "fingerprint": "b21e619da904" }, { "url": "https://www.speechmatics.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:52:23.766060542Z", "changedAt": "2026-10-02T15:28:26.363072685Z", "fingerprint": "535f1bf23b91" }, { "url": "https://www.speechmatics.com/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:52:19.517199363Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3af3999aaeb0" }, { "url": "https://www.speechmatics.com/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:52:21.66336211Z", "changedAt": "2026-10-02T15:28:24.437639084Z", "fingerprint": "33b19ec6fdcb" } ], "updatedAt": "2026-10-04T22:35:31.760482402Z" } }, { "slug": "assemblyai-stt", "name": "AssemblyAI Speech-to-Text (Universal)", "vendor": "AssemblyAI", "vendorUrl": "https://www.assemblyai.com", "kind": "model", "category": "speech-to-text", "summary": "Speech-to-text APIs for recorded audio and live streams, with speaker identification, translation and redaction options.", "url": "https://www.anchorterminal.com/tools/assemblyai-stt", "markdownUrl": "https://www.anchorterminal.com/tools/assemblyai-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/assemblyai-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/assemblyai-stt.json", "repo": "https://github.com/AssemblyAI/assemblyai-python-sdk", "license": "MIT (SDKs)", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.assemblyai.com/v2", "packages": [ { "registry": "npm", "name": "assemblyai" }, { "registry": "pypi", "name": "assemblyai" } ], "auth": "api-key", "authNotes": "API key in the `authorization` header. Temporary tokens for browser streaming. The docs MCP needs no key.", "pricing": "usage", "pricingNotes": "Free tier with no card covers up to 185 hours of pre-recorded or 333 hours of streaming. Then pay as you go per hour of audio. Universal-3.5 Pro $0.21, Universal-2 $0.15, Universal-3.6 Pro Realtime $0.45, Universal-Streaming $0.15, Sync $0.45. Diarisation $0.02 an hour on files and $0.12 on streams, keyterms $0.05 on Universal-3.5 Pro, translation $0.06. Streaming bills session time, not audio sent (https://www.assemblyai.com/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 213, "npmWeekly": 599958, "pypiWeekly": 738086, "asOf": "2026-09-30" }, "docsUrl": "https://www.assemblyai.com/docs", "llmsTxt": "https://www.assemblyai.com/docs/llms.txt", "openapi": "https://www.assemblyai.com/docs/openapi.yaml", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "no-card", "free-tier", "closed-source", "python", "typescript", "openapi", "llms-txt", "mcp", "streaming", "batch", "webhooks", "async-jobs", "enterprise" ], "lastRelease": "2026-09-24", "graded": true, "anchor": { "graded": true, "score": 67, "grade": "B", "agentReady": false, "rank": 148, "ranked": true, "rankOf": 452, "categoryRank": 8, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 80, "payments": 40, "reliability": 70, "schema": 95, "security": 50, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -3, "negativeNotes": [ "2026-07-10, the async `speech_model` parameter began returning 400 for current model names and silently routing legacy names to the default model, and `universal-3-pro` was blocked for new accounts and accounts inactive for 7 days, all announced in the changelog the same day. We found no earlier notice (https://www.assemblyai.com/changelog). Documented, so the minimum deduction." ], "verdict": "OpenAPI 3.1 file with typed inputs and error responses on every operation. Two outages of an hour or more in the last 90 days, on 31 July and 16 September 2026.", "strengths": [ "OpenAPI 3.1 file with typed inputs and error responses on every operation", "Universal-2 covers 99 languages at $0.15 an hour, Universal-3.5 Pro is $0.21", "Transcript lists paginate with `limit`, `before_id` and `after_id`, and transcripts come back as sentences, paragraphs, SRT or VTT", "Free tier with no card, up to 185 hours pre-recorded", "TTL deletion from 1 hour and a delete endpoint for transcripts" ], "weaknesses": [ "Two outages of an hour or more in the last 90 days, on 31 July and 16 September 2026", "Free accounts can't opt out of model training", "The HTTP rate limit returns 403 with no Retry-After", "Streaming bills the time the socket is open, up to a 3-hour auto-close", "No security.txt or published disclosure policy" ], "agentNotes": [ "Send `{\"type\":\"Terminate\"}` to close every stream, or billing runs to the 3-hour auto-close", "Use `speech_models` (plural). The singular `speech_model` now returns 400 for current model names", "Treat a 403 on polling as the rate limit and back off with jitter, or use webhooks", "Fetch `/sentences` or `/paragraphs` instead of the full transcript when you only need text", "Opt out in Data Controls on a paid account before sending customer audio" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67 } ], "editorialScores": { "ergonomics": 80, "maintenance": 80, "payments": 40, "reliability": 70, "schema": 95, "security": 50, "transparency": 70 }, "provenanceScore": 86 }, "connect": { "http": "curl -X POST https://api.assemblyai.com/v2/transcript -H \"authorization: $ASSEMBLYAI_API_KEY\" \\\n -H \"content-type: application/json\" \\\n -d '{\"audio_url\":\"https://assembly.ai/wildfires.mp3\",\"language_detection\":true,\"speaker_labels\":true}'", "claudeCode": "claude mcp add assemblyai-docs --transport http https://assemblyai.com/docs/mcp" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/assemblyai-stt" }, "area": "voice", "unitPrices": [ { "item": "Universal-3.5 Pro pre-recorded", "unit": "audio-minute", "usd": 0.0035, "note": "published as $0.21 an hour" }, { "item": "Universal-2 pre-recorded", "unit": "audio-minute", "usd": 0.0025, "note": "published as $0.15 an hour" }, { "item": "Universal-3.6 Pro Realtime", "unit": "audio-minute", "usd": 0.0075, "note": "published as $0.45 an hour, billed on session time" }, { "item": "Universal-Streaming", "unit": "audio-minute", "usd": 0.0025, "note": "published as $0.15 an hour, billed on session time" }, { "item": "Sync API", "unit": "audio-minute", "usd": 0.0075, "note": "published as $0.45 an hour, clips up to 2 minutes" }, { "item": "Streaming diarisation add-on", "unit": "audio-minute", "usd": 0.002, "note": "published as $0.12 an hour" } ], "provenance": { "legalEntity": "AssemblyAI, Inc.", "domain": "assemblyai.com", "domainRegistered": "2016-12-24", "endpointOnVendorDomain": true, "terms": "https://www.assemblyai.com/legal/terms-of-service", "privacy": "https://www.assemblyai.com/legal/privacy-policy", "statusPage": "https://status.assemblyai.com", "changelog": "https://www.assemblyai.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/assemblyai-stt.json", "live": { "slug": "assemblyai-stt", "probe": { "target": "https://api.assemblyai.com/v2", "method": "get", "lastAt": "2026-10-04T22:35:18.919300566Z", "lastOk": true, "lastStatus": 404, "lastMs": 440, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 443, "p95ms24h": 486, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.assemblyai.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:33:46.730370035Z" }, "versions": [ { "registry": "github", "name": "AssemblyAI/assemblyai-python-sdk", "version": "1.6.1", "released": "2026-09-24", "seenAt": "2026-10-04T16:20:56.490457181Z" }, { "registry": "npm", "name": "assemblyai", "version": "4.41.5", "seenAt": "2026-10-04T16:20:55.58059221Z" }, { "registry": "pypi", "name": "assemblyai", "version": "1.6.1", "released": "2026-09-24", "seenAt": "2026-10-04T16:20:56.382722009Z" } ], "githubStars": 213, "npmWeekly": 645780, "pypiWeekly": 817313, "securityTxt": { "url": "https://assemblyai.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:16:02.784112938Z" }, "llmsTxt": { "url": "https://www.assemblyai.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:15.941338129Z" }, "domain": { "domain": "assemblyai.com", "registered": "2016-12-24", "source": "https://rdap.verisign.com/com/v1/domain/assemblyai.com", "checkedAt": "2026-10-04T13:07:48.940216522Z" }, "pages": [ { "url": "https://www.assemblyai.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-04T15:49:11.730936349Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f7dbbe98a56a" }, { "url": "https://www.assemblyai.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:49:17.853952095Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "07bb01ccd4d1" }, { "url": "https://www.assemblyai.com/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:49:13.761556773Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6671be50624e" }, { "url": "https://www.assemblyai.com/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-04T15:49:15.761345368Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "766c6ee47ebc" } ], "updatedAt": "2026-10-04T22:35:18.919300566Z" } }, { "slug": "soniox-stt", "name": "Soniox Speech-to-Text", "vendor": "Soniox", "vendorUrl": "https://soniox.com", "kind": "model", "category": "speech-to-text", "summary": "One multilingual model family for 60+ languages, as a real-time WebSocket API (`stt-rt-v5`) and an async file API (`stt-async-v5`).", "url": "https://www.anchorterminal.com/tools/soniox-stt", "markdownUrl": "https://www.anchorterminal.com/tools/soniox-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/soniox-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/soniox-stt.json", "repo": "https://github.com/soniox/soniox-python", "license": "Apache-2.0 (Python SDK)", "transports": [ "http" ], "remoteUrl": "https://api.soniox.com/v1", "packages": [ { "registry": "npm", "name": "@soniox/node" }, { "registry": "pypi", "name": "soniox" } ], "auth": "api-key", "authNotes": "Bearer API key per project. Temporary API keys can be minted for browsers and mobile clients that stream straight to `wss://stt-rt.soniox.com`. Regional projects get their own keys and domains (EU, Japan, India).", "pricing": "usage", "pricingNotes": "Token-based pay-as-you-go. Async audio input $1.50 per 1M tokens and text in or out $3.50 per 1M, real-time $2.00 and $4.00. Soniox puts this at about $0.10 an hour async and $0.12 an hour real-time, with diarisation, language ID and translation included. New sign-ups have had no free credits since 2025-10-27 (https://soniox.com/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Billed to a funded account (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 12, "npmWeekly": 22200, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://soniox.com/docs/stt/get-started", "llmsTxt": "https://soniox.com/docs/llms.txt", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "closed-source", "python", "typescript", "llms-txt", "webhooks", "async-jobs", "streaming", "batch", "enterprise" ], "lastRelease": "2026-08-11", "graded": true, "anchor": { "graded": true, "score": 58.3, "grade": "C", "agentReady": false, "rank": 281, "ranked": true, "rankOf": 452, "categoryRank": 9, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 30, "payments": 20, "reliability": 65, "schema": 60, "security": 70, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included. No free credits for new accounts since October 2025.", "strengths": [ "About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included", "Customer audio and transcripts are never used for training, and nothing is retained by default", "SOC 2 Type 2 and ISO/IEC 27001:2022", "Regional deployments in the US, EU, Japan and India", "Per-request usage logs with cost and request IDs" ], "weaknesses": [ "No free credits for new accounts since October 2025", "No OpenAPI or AsyncAPI file", "No documented status code, Retry-After or backoff for rate limits", "10 concurrent streams and a fixed 300-minute cap per stream or file", "No STT changelog entry since June 2026" ], "agentNotes": [ "Pass `audio_url` for public files and skip the upload step. Delete uploaded files or they count against the 10 GB quota for 30 days", "Use the `context` field for names and domain terms", "Buffer audio while the WebSocket connects, then flush it after the config message", "Split anything over 300 minutes. The cap is fixed", "Set `client_reference_id` so failed or duplicate requests can be traced in the usage log" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.3 } ], "editorialScores": { "ergonomics": 70, "maintenance": 30, "payments": 20, "reliability": 65, "schema": 60, "security": 70, "transparency": 70 }, "provenanceScore": 86 }, "connect": { "http": "curl https://api.soniox.com/v1/transcriptions -H \"Authorization: Bearer $SONIOX_API_KEY\" \\\n -H \"content-type: application/json\" \\\n -d '{\"model\":\"stt-async-v5\",\"audio_url\":\"https://soniox.com/media/examples/coffee_shop.mp3\",\"enable_speaker_diarization\":true}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/soniox-stt" }, "sameCompany": [ "soniox-tts", "soniox-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "stt-async-v5", "unit": "audio-minute", "usd": 0.0017, "note": "Soniox's estimate of $0.10 an hour, token-billed" }, { "item": "stt-rt-v5 streaming", "unit": "audio-minute", "usd": 0.002, "note": "Soniox's estimate of $0.12 an hour, token-billed" } ], "provenance": { "legalEntity": "Soniox Inc.", "domain": "soniox.com", "domainRegistered": "2020-03-23", "endpointOnVendorDomain": true, "terms": "https://soniox.com/policies/terms-of-service", "privacy": "https://soniox.com/policies/privacy-policy", "statusPage": "https://status.soniox.com", "changelog": "https://soniox.com/docs/stt/models", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms and privacy policy last updated 2026-06-29. The company address is Foster City, California" ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/soniox-stt.json", "live": { "slug": "soniox-stt", "probe": { "target": "https://api.soniox.com/v1", "method": "get", "lastAt": "2026-10-04T22:35:31.434879788Z", "lastOk": true, "lastStatus": 404, "lastMs": 252, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 254, "p95ms24h": 333, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.soniox.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-04T21:40:29.486491004Z" }, "versions": [ { "registry": "npm", "name": "@soniox/node", "version": "2.3.0", "seenAt": "2026-10-04T16:40:11.459304536Z" }, { "registry": "pypi", "name": "soniox", "version": "2.10.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:40:12.365123068Z" } ], "githubStars": 12, "npmWeekly": 26180, "pypiWeekly": 171250, "securityTxt": { "url": "https://soniox.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:59.988207849Z" }, "llmsTxt": { "url": "https://soniox.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:14.627818873Z" }, "domain": { "domain": "soniox.com", "registered": "2020-03-23", "source": "https://rdap.verisign.com/com/v1/domain/soniox.com", "checkedAt": "2026-10-04T13:05:00.531232044Z" }, "pages": [ { "url": "https://soniox.com/blog/2025-10-27-free-credits-update-for-soniox-api", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-04T15:47:56.380896752Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "84edd3460b10" }, { "url": "https://soniox.com/docs/stt/models", "kind": "deprecations", "status": 304, "checkedAt": "2026-10-04T15:47:58.72062751Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "bc23abf2e34e" }, { "url": "https://soniox.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-04T15:48:06.860520103Z", "changedAt": "2026-10-02T15:24:18.034370139Z", "fingerprint": "3c5bced7754b" }, { "url": "https://soniox.com/policies/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:48:02.465957121Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f8449bf14df5" }, { "url": "https://soniox.com/policies/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:48:05.013237203Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1ab8c9d50b68" } ], "updatedAt": "2026-10-04T22:35:31.434879788Z" } }, { "slug": "rev-ai-stt", "name": "Rev AI Speech-to-Text API", "vendor": "Rev", "vendorUrl": "https://www.rev.ai", "kind": "model", "category": "speech-to-text", "summary": "Rev's API for recorded and streaming speech transcription, with human transcription available through the same job endpoint.", "url": "https://www.anchorterminal.com/tools/rev-ai-stt", "markdownUrl": "https://www.anchorterminal.com/tools/rev-ai-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/rev-ai-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/rev-ai-stt.json", "repo": "https://github.com/revdotcom/revai-python-sdk", "license": "MIT (SDKs)", "transports": [ "http" ], "remoteUrl": "https://api.rev.ai/speechtotext/v1", "packages": [ { "registry": "npm", "name": "revai-node-sdk" }, { "registry": "pypi", "name": "rev_ai" } ], "auth": "api-key", "authNotes": "Bearer access token for REST. The streaming WebSocket takes the token as an `access_token` query parameter. EU deployment at `ec1.api.rev.ai` with its own account.", "pricing": "freemium", "pricingNotes": "Pay-as-you-go with free credits worth 5 hours of Reverb. Reverb English $0.20 an hour, Reverb foreign language $0.30 an hour, Whisper Large $0.005 a minute, human transcription $1.99 a minute (rush +$1.25, verbatim +$0.50). Billed per second with a 15-second minimum. Streaming bills the longer of stream time and audio time (https://www.rev.ai/pricing).", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Billed to a funded account (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 36, "npmWeekly": 16176, "pypiWeekly": 129624, "asOf": "2026-09-30" }, "docsUrl": "https://docs.rev.ai", "llmsTxt": "https://docs.rev.ai/llms.txt", "openapi": "https://docs.rev.ai/_bundle/api/asynchronous/reference.yaml", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages", "speech.translation" ], "tags": [ "hosted", "freemium", "llms-txt", "python", "typescript", "webhooks", "async-jobs", "streaming", "batch", "enterprise", "open-weights" ], "lastRelease": "2024-11-27", "graded": true, "anchor": { "graded": true, "score": 58, "grade": "C", "agentReady": false, "rank": 285, "ranked": true, "rankOf": 452, "categoryRank": 10, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 30, "payments": 20, "reliability": 75, "schema": 80, "security": 40, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Reverb English at $0.20 an hour, foreign languages at $0.30. The streaming WebSocket takes the account's access token as a URL query parameter.", "strengths": [ "Reverb English at $0.20 an hour, foreign languages at $0.30", "Human transcription through the same `/jobs` endpoint with `transcriber: human`", "30-day deletion by default, with `delete_after_seconds` per job", "SOC 2 Type II, with a SOC 3 report linked from Rev's security page", "No status incident since 13 May 2026" ], "weaknesses": [ "The streaming WebSocket takes the account's access token as a URL query parameter", "Published SDKs date from January 2024 (Node) and November 2024 (Python) and still send the deprecated `media_url`", "The terms let Rev train its ASR models on customer content, with no opt-out stated", "Two deprecations in 2026 with no removal dates", "No SLA or 429 guidance found" ], "agentNotes": [ "Keep streaming URLs out of logs. They carry `access_token`", "Send `source_config: {\"url\": ...}`, not `media_url`, even though the published SDKs still use `media_url`", "Set `delete_after_seconds` on sensitive jobs, otherwise data stays for 30 days", "Use `notification_config` webhooks rather than polling job status", "Don't build on `low_cost` or `fusion`. Both are deprecated" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58 } ], "editorialScores": { "ergonomics": 72, "maintenance": 30, "payments": 20, "reliability": 75, "schema": 80, "security": 40, "transparency": 55 }, "provenanceScore": 86 }, "connect": { "http": "curl https://api.rev.ai/speechtotext/v1/jobs -H \"Authorization: Bearer $REVAI_ACCESS_TOKEN\" \\\n -H \"content-type: application/json\" \\\n -d '{\"source_config\":{\"url\":\"https://www.rev.ai/FTC_Sample_1.mp3\"}}'" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/rev-ai-stt" }, "area": "voice", "unitPrices": [ { "item": "Reverb English", "unit": "audio-minute", "usd": 0.0033, "note": "published as $0.20 an hour" }, { "item": "Reverb foreign language", "unit": "audio-minute", "usd": 0.005, "note": "published as $0.30 an hour, async" }, { "item": "Whisper Large", "unit": "audio-minute", "usd": 0.005, "note": "English" }, { "item": "Human transcription", "unit": "audio-minute", "usd": 1.99, "note": "English, rush +$1.25 and verbatim +$0.50 a minute" } ], "provenance": { "legalEntity": "Rev.com, Inc.", "domain": "rev.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://www.rev.com/legal/terms", "privacy": "https://www.rev.com/legal/privacy", "statusPage": "https://status.rev.ai", "changelog": "https://docs.rev.ai/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Rev AI is governed by the Rev.com terms of service, last updated 2026-05-15. rev.com was registered in 1998" ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/rev-ai-stt.json", "live": { "slug": "rev-ai-stt", "probe": { "target": "https://api.rev.ai/speechtotext/v1", "method": "get", "lastAt": "2026-10-04T22:35:30.366777153Z", "lastOk": true, "lastStatus": 404, "lastMs": 588, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 589, "p95ms24h": 631, "samples24h": 272, "samples30d": 1086, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 256, "ok": 256 } ] }, "vendorStatus": { "page": "https://status.rev.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T22:34:07.681242145Z" }, "versions": [ { "registry": "npm", "name": "revai-node-sdk", "version": "3.8.5", "seenAt": "2026-10-04T16:38:35.402899531Z" }, { "registry": "pypi", "name": "rev_ai", "version": "2.21.0", "released": "2024-11-27", "seenAt": "2026-10-04T16:38:36.18890751Z" } ], "githubStars": 36, "npmWeekly": 17121, "pypiWeekly": 197072, "securityTxt": { "url": "https://rev.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:57.851025679Z" }, "llmsTxt": { "url": "https://docs.rev.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:11.899175915Z" }, "domain": { "domain": "rev.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/rev.ai", "checkedAt": "2026-10-04T13:07:46.912041316Z" }, "pages": [ { "url": "https://docs.rev.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:43:59.889982136Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8d345a683984" }, { "url": "https://docs.rev.ai/api/asynchronous/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-04T15:43:57.740079837Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9b75caf8279c" }, { "url": "https://www.rev.ai/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-04T15:51:56.636649367Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "cb94b28a4717" }, { "url": "https://www.rev.com/legal/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-04T15:51:56.814347332Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "91d0af3ad838" }, { "url": "https://www.rev.com/legal/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-04T15:51:58.876573403Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f2fbc35b763b" } ], "updatedAt": "2026-10-04T22:35:30.366777153Z" } } ] }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/categories/speech-to-text", "json": "https://www.anchorterminal.com/categories/speech-to-text.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/categories/speech-to-text.md", "slim": "https://www.anchorterminal.com/categories/speech-to-text.min.md" }, "markdown": "APIs that turn audio into text, streaming or in batch. Compared on accuracy across accents, noise, names and overlapping speakers, streaming latency, languages, diarisation and cost per audio minute.\n\n- Tools ranked: 10 · agent-ready (BB or better): 4 · accept x402: 0 · hosted endpoints: 10 · desk reviews by the panel: 26\n- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)\n- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/\n\n- Capabilities in this category: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages\n- https://letme.dev/speech.stt picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)\n\n## Ranking\n\n| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 23 | Azure AI Speech speech-to-text | Microsoft Azure | Model API | STT | BB | 77 | medium | no | OAuth or key | hosted | 3.3/5 (8) | https://www.anchorterminal.com/tools/azure-speech-to-text.md |\n| 57 | Amazon Transcribe | Amazon Web Services | Model API | STT | BB | 73.6 | medium | no | API key | hosted | 4/5 (2) | https://www.anchorterminal.com/tools/amazon-transcribe.md |\n| 94 | Deepgram Speech-to-Text (Nova-3, Flux) | Deepgram | Model API | STT | BB | 70.6 | medium | no | API key | hosted + local | 3.5/5 (2) | https://www.anchorterminal.com/tools/deepgram-stt.md |\n| 98 | Google Cloud Speech-to-Text | Google Cloud | Model API | STT | BB | 70.4 | medium | no | OAuth | hosted | 3/5 (2) | https://www.anchorterminal.com/tools/google-speech-to-text.md |\n| 108 | Gladia Speech-to-Text API + MCP | Gladia | Model API | STT | B | 69.7 | medium | no | API key | hosted + local | 3/5 (2) | https://www.anchorterminal.com/tools/gladia-stt.md |\n| 117 | ElevenLabs Scribe Speech to Text API | ElevenLabs | Model API | STT | B | 69 | medium | no | API key | hosted + local | 3.5/5 (2) | https://www.anchorterminal.com/tools/elevenlabs-scribe.md |\n| 145 | Speechmatics Speech-to-Text | Speechmatics | Model API | STT | B | 67.3 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/speechmatics-stt.md |\n| 148 | AssemblyAI Speech-to-Text (Universal) | AssemblyAI | Model API | STT | B | 67 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/assemblyai-stt.md |\n| 281 | Soniox Speech-to-Text | Soniox | Model API | STT | C | 58.3 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/soniox-stt.md |\n| 285 | Rev AI Speech-to-Text API | Rev | Model API | STT | C | 58 | medium | no | API key | hosted | 2.5/5 (2) | https://www.anchorterminal.com/tools/rev-ai-stt.md |\n\nScores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.\n\n## Summaries\n\n### 23. Azure AI Speech speech-to-text, BB (77)\n\nAzure's speech-to-text service for transcribing audio. Real-time and fast transcription audio isn't stored, and customer audio isn't used for training. MAI-Transcribe-2 is preview with no SLA, and its $0.10 promotional price ends on 2026-12-31.\n\n- Page: https://www.anchorterminal.com/tools/azure-speech-to-text · Markdown: https://www.anchorterminal.com/tools/azure-speech-to-text.md · JSON: https://www.anchorterminal.com/api/v1/tools/azure-speech-to-text.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://eastus.api.cognitive.microsoft.com/speechtotext`\n\n### 57. Amazon Transcribe, BB (73.6)\n\nAWS's transcription API. $0.006 a minute batch and $0.01 streaming in US East, with diarisation, custom vocabulary and language ID included. AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set.\n\n- Page: https://www.anchorterminal.com/tools/amazon-transcribe · Markdown: https://www.anchorterminal.com/tools/amazon-transcribe.md · JSON: https://www.anchorterminal.com/api/v1/tools/amazon-transcribe.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages · endpoint: `https://transcribe.us-east-1.amazonaws.com`\n\n### 94. Deepgram Speech-to-Text (Nova-3, Flux), BB (70.6)\n\nDeepgram's speech-to-text API for recorded audio and live streams, including turn detection for voice agents. Flux streams with model-level end-of-turn detection, so a voice agent needs no separate VAD. Training on audio is the default and the opt-out is a per-request flag.\n\n- Page: https://www.anchorterminal.com/tools/deepgram-stt · Markdown: https://www.anchorterminal.com/tools/deepgram-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/deepgram-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages · endpoint: `https://api.deepgram.com/v1`\n\n### 98. Google Cloud Speech-to-Text, BB (70.4)\n\nGoogle Cloud's transcription API. Audio isn't stored or used for training unless the project opts in to data logging. No release note since 2025-11-13.\n\n- Page: https://www.anchorterminal.com/tools/google-speech-to-text · Markdown: https://www.anchorterminal.com/tools/google-speech-to-text.md · JSON: https://www.anchorterminal.com/api/v1/tools/google-speech-to-text.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://speech.googleapis.com/v2`\n\n### 108. Gladia Speech-to-Text API + MCP, B (69.7)\n\nSpeech-to-text API for live and recorded audio, with multilingual transcription and code switching. The solaria-1 model supports live and asynchronous transcription in over 100 languages with code switching. Starter pricing is $0.61 an hour for asynchronous transcription and $0.75 for real-time audio.\n\n- Page: https://www.anchorterminal.com/tools/gladia-stt · Markdown: https://www.anchorterminal.com/tools/gladia-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/gladia-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://api.gladia.io/v2`\n\n### 117. ElevenLabs Scribe Speech to Text API, B (69)\n\nElevenLabs' speech-to-text service for audio transcription. $0.22 an hour for batch with 90+ languages and diarisation to 32 speakers. Audio may be used for training unless the account opts out, and the opt-out isn't retroactive.\n\n- Page: https://www.anchorterminal.com/tools/elevenlabs-scribe · Markdown: https://www.anchorterminal.com/tools/elevenlabs-scribe.md · JSON: https://www.anchorterminal.com/api/v1/tools/elevenlabs-scribe.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages · endpoint: `https://api.elevenlabs.io/v1`\n\n### 145. Speechmatics Speech-to-Text, B (67.3)\n\nSpeechmatics' APIs for batch and real-time transcription, including speaker-attributed turns for voice agents. Training is opt-in and real-time audio is not stored. Enhanced transcription costs $0.40 to $0.43 an hour.\n\n- Page: https://www.anchorterminal.com/tools/speechmatics-stt · Markdown: https://www.anchorterminal.com/tools/speechmatics-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/speechmatics-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://eu1.asr.api.speechmatics.com/v2`\n\n### 148. AssemblyAI Speech-to-Text (Universal), B (67)\n\nSpeech-to-text APIs for recorded audio and live streams, with speaker identification, translation and redaction options. OpenAPI 3.1 file with typed inputs and error responses on every operation. Two outages of an hour or more in the last 90 days, on 31 July and 16 September 2026.\n\n- Page: https://www.anchorterminal.com/tools/assemblyai-stt · Markdown: https://www.anchorterminal.com/tools/assemblyai-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/assemblyai-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://api.assemblyai.com/v2`\n\n### 281. Soniox Speech-to-Text, C (58.3)\n\nOne multilingual model family for 60+ languages, as a real-time WebSocket API (`stt-rt-v5`) and an async file API (`stt-async-v5`). About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included. No free credits for new accounts since October 2025.\n\n- Page: https://www.anchorterminal.com/tools/soniox-stt · Markdown: https://www.anchorterminal.com/tools/soniox-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/soniox-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://api.soniox.com/v1`\n\n### 285. Rev AI Speech-to-Text API, C (58)\n\nRev's API for recorded and streaming speech transcription, with human transcription available through the same job endpoint. Reverb English at $0.20 an hour, foreign languages at $0.30. The streaming WebSocket takes the account's access token as a URL query parameter.\n\n- Page: https://www.anchorterminal.com/tools/rev-ai-stt · Markdown: https://www.anchorterminal.com/tools/rev-ai-stt.md · JSON: https://www.anchorterminal.com/api/v1/tools/rev-ai-stt.json\n- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation · endpoint: `https://api.rev.ai/speechtotext/v1`\n\n## How we test this category\n\nThe same audio set through every API, with accents, background noise, proper names and overlapping speakers. We measure word error rate on each slice, streaming latency to a final transcript, and cost per audio minute. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.\n\n## Indexed, not reviewed (20)\n\nSorted into this category from public catalogues, with facts and our own checks but no score, grade or rank (https://www.anchorterminal.com/indexed/index.md).\n\n| Listing | Kind | What it does | Why it's here |\n| --- | --- | --- | --- |\n| [2kw.ai](https://www.anchorterminal.com/tools/2kw-mcp-server.md) | MCP server | EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents. | vendor's own, widely used |\n| [backengine-mcp](https://www.anchorterminal.com/tools/backengine-mcp.md) | MCP server | Surface customer \u0026 prospect context from Slack, email, transcripts and tickets in any MCP client. | vendor's own |\n| [Bigdata.com](https://www.anchorterminal.com/tools/bigdata-mcp.md) | MCP server | Licensed, cited financial data for AI agents: news, filings, transcripts, research and tearsheets. | vendor's own |\n| [Cleat](https://www.anchorterminal.com/tools/cleat.md) | MCP server | A real US mobile number that receives verification codes, by text or transcribed call. | vendor's own |\n| [clipy.online MCP server](https://www.anchorterminal.com/tools/clipy-mcp.md) | MCP server | Read your Clipy screen recordings: search, transcripts, AI summaries, and key moments with frames. | vendor's own |\n| [Cortex RMCP](https://www.anchorterminal.com/tools/dinglebear-cortex-rmcp.md) | MCP server | Rust MCP server for homelab logs, syslog, Docker logs, FTS search, and AI transcript correlation. | vendor's own |\n| [Crixin Voice](https://www.anchorterminal.com/tools/crixin-voice.md) | MCP server | Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted. | vendor's own |\n| [DialMCP](https://www.anchorterminal.com/tools/dialmcp.md) | MCP server | Let AI agents place real phone calls from your verified number, with transcripts and recordings. | vendor's own |\n| [Gavelin](https://www.anchorterminal.com/tools/gavelin-mcp.md) | MCP server | Search bills and speaker-attributed hearing transcripts across all 50 US state legislatures. | vendor's own |\n| [importly-mcp](https://www.anchorterminal.com/tools/importly-mcp.md) | MCP server | Download, transcribe, and get metadata for any video/audio URL. Managed yt-dlp + speech-to-text. | vendor's own |\n| [Memo AI – meeting assistant](https://www.anchorterminal.com/tools/memoai-memo-ai.md) | MCP server | Search transcripts and summaries of your meetings, calls, and recordings in Memo AI | vendor's own |\n| [pepys-mcp](https://www.anchorterminal.com/tools/pepys-mcp.md) | MCP server | Transcribe audio \u0026 video: diarization, timed SRT/VTT, podcasts, paste-a-link, whole-feed batch. | vendor's own |\n| [Rephonic](https://www.anchorterminal.com/tools/rephonic.md) | MCP server | Research 3M+ podcasts with audience data, contacts, episodes, transcripts, charts, and sponsors. | vendor's own |\n| [SOAPNoteAPI](https://www.anchorterminal.com/tools/soapnoteapi-mcp.md) | MCP server | Generate clinical SOAP notes, billing codes, and visit summaries from transcripts or audio. | vendor's own |\n| [transcription](https://www.anchorterminal.com/tools/scriptivox-transcription.md) | MCP server | AI transcription from URLs or files. 119 languages, diarization, SRT/VTT/text export. | vendor's own |\n| [Vexa](https://www.anchorterminal.com/tools/vexa.md) | MCP server | Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled. | vendor's own, widely used |\n| [Video Extract](https://www.anchorterminal.com/tools/yanlinglabs-video-extract-mcp.md) | MCP server | Download any video from a URL, or get its transcript and key frames. All local, no API keys. | vendor's own |\n| [Voxplo](https://www.anchorterminal.com/tools/voxplo.md) | MCP server | Give AI agents a phone: outbound AI calls that return a summary, transcript, and extracted fields. | vendor's own |\n| [YouTube Transcript + YouTube Search MCP](https://www.anchorterminal.com/tools/getyoutubetranscript-youtube-transcript-and-youtube-search.md) | MCP server | YouTube transcripts, search, channel browsing, and playlists for AI agents via MCP. | vendor's own |\n| [💯 YouTube Transcript + YouTube Search MCP for AI Agents](https://www.anchorterminal.com/tools/transcriptapi-youtube-transcript-and-youtube-search.md) | MCP server | 💯 The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. | vendor's own |\n\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-04", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Speech-to-text", "url": "" } ], "description": "10 speech-to-text listings ranked by the Anchor benchmark. Leader Azure AI Speech speech-to-text (BB). APIs that turn audio into text, streaming or in batch. Compared on accuracy across accents, noise, names and overlapping speakers, streaming latency, languages, diarisation and cost per audio minute.", "facts": [ "Azure AI Speech speech-to-text BB", "Amazon Transcribe BB", "Deepgram Speech-to-Text (Nova-3, Flux) BB" ], "h1": "Speech-to-text APIs for AI agents", "image": "https://www.anchorterminal.com/assets/og/categories-speech-to-text.png", "path": "/categories/speech-to-text", "published": "", "section": "tools", "title": "Speech-to-text APIs for AI agents, ranked | Anchor Terminal", "toc": null, "updated": "2026-10-04", "url": "https://www.anchorterminal.com/categories/speech-to-text" }, "tokens": { "markdown": 3850, "slim": 580 }, "version": 1 }