{ "data": { "a": { "slug": "groq-speech-to-text", "name": "Groq Speech-to-Text", "vendor": "Groq", "vendorUrl": "https://groq.com", "kind": "model", "category": "speech-to-text", "summary": "Groq's hosted speech-to-text API. It runs OpenAI's Whisper Large v3 and Whisper Large v3 Turbo on OpenAI-compatible transcription and translation endpoints, for uploaded files or audio URLs, with a half-price batch mode.", "url": "https://www.anchorterminal.com/tools/groq-speech-to-text", "markdownUrl": "https://www.anchorterminal.com/tools/groq-speech-to-text.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/groq-speech-to-text.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/groq-speech-to-text.json", "dns": "groq-speech-to-text.grade.anchorterminal.com", "repo": "https://github.com/groq/groq-python", "license": "Proprietary hosted service under the Groq Services Agreement. The SDKs are Apache-2.0 and the Whisper weights are published by OpenAI on Hugging Face", "transports": [ "http" ], "remoteUrl": "https://api.groq.com/openai/v1", "packages": [ { "registry": "pypi", "name": "groq" }, { "registry": "npm", "name": "groq-sdk" } ], "auth": "api-key", "authNotes": "Self-serve bearer key from the GroqCloud console, created inside a project. Projects carry their own rate limits per model, usage data and request logs (https://console.groq.com/docs/projects).", "pricing": "freemium", "pricingNotes": "$0.04 per audio hour for Whisper Large v3 Turbo and $0.111 for Whisper Large v3, with a 10-second minimum a request and 50% off through the Batch API (https://console.groq.com/docs/models). The free plan needs no card, so an agent's owner can start without a contract. The Developer plan is postpaid by card, US bank account or SEPA debit.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the speech-to-text guide, the API reference or the billing pages (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 621, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://console.groq.com/docs/speech-to-text", "llmsTxt": "https://console.groq.com/llms.txt", "capabilities": [ "speech.stt", "speech.batch", "speech.languages" ], "tags": [ "official", "hosted", "model", "fast", "free-tier", "no-card", "llms-txt", "python", "typescript", "batch", "openai-compatible" ], "lastRelease": "2026-08-26", "graded": true, "anchor": { "graded": true, "score": 70.1, "grade": "BB", "agentReady": true, "rank": 211, "ranked": true, "rankOf": 1486, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 48, "payments": 40, "reliability": 90, "schema": 58, "security": 79, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Whisper Large v3 Turbo costs $0.04 an audio hour and Whisper Large v3 $0.111, with a no-card free plan and zero data retention as a self-serve setting. There is no streaming endpoint, no diarisation and no subtitle output, and uploads stop at 25 MB on the free plan and 100 MB on the Developer plan.", "bestFor": "Suited to cheap, fast transcription of recorded files in many languages, and to agents that already hold a Groq key or use an OpenAI-compatible client.", "strengths": [ "Published prices of $0.04 an audio hour for Whisper Large v3 Turbo and $0.111 for Whisper Large v3, with 50% off through the Batch API", "Free plan with no card at 20 requests a minute, 2,000 a day and 7,200 audio seconds an hour on both models", "Inputs and outputs are not retained by default, and zero data retention is a console setting that covers both audio endpoints", "The status page lists each Whisper model as its own component, both at 100% uptime for August to November 2026", "OpenAI-compatible request shape, with `model` and a `file` or `url` as the only required fields" ], "weaknesses": [ "No streaming or realtime endpoint and no diarisation in the reviewed documentation", "Uploads are capped at 25 MB on the free plan and 100 MB on the Developer plan, so long recordings need client-side chunking", "`srt` and `vtt` response formats are not supported, and Whisper Large v3 Turbo cannot translate", "No OpenAPI document was found, and the docs changelog's newest entry is dated 18 April", "The 99.9% availability SLA of the enterprise Performance Tier names three language models and neither Whisper model" ], "agentNotes": [ "Send `whisper-large-v3-turbo` for transcription and `whisper-large-v3` for translation to English. The translations endpoint does not accept Turbo.", "Pass `url` instead of `file` for audio over 25 MB, and split anything over the plan's size limit into overlapping chunks before sending.", "Set `response_format` to `verbose_json` before asking for `timestamp_granularities[]`. Word timestamps add latency, segment timestamps do not.", "Every request is billed as at least 10 seconds of audio, so join very short clips where the task allows.", "Read `retry-after` on a 429 and back off. Audio limits count seconds an hour and a day as well as requests." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.1 } ], "editorialScores": { "ergonomics": 75, "maintenance": 48, "payments": 40, "reliability": 90, "schema": 58, "security": 79, "transparency": 72 }, "provenanceScore": 98, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install groq # or: npm install --save groq-sdk", "http": "curl https://api.groq.com/openai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -F file=\"@./sample_audio.m4a\" \\\n -F model=\"whisper-large-v3\"" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/groq-speech-to-text" }, "sameCompany": [ "groq" ], "area": "voice", "unitPrices": [ { "item": "Whisper Large v3 Turbo ($0.04 an audio hour)", "unit": "audio-minute", "usd": 0.000667 }, { "item": "Whisper Large v3 ($0.111 an audio hour)", "unit": "audio-minute", "usd": 0.00185 } ], "provenance": { "legalEntity": "Groq LLC", "domain": "groq.com", "domainRegistered": "2007-07-22", "domainNote": "The registration date is per the 26 September check of the GroqCloud listing and was not re-read on 8 October. groq.com was registered before Groq existed. Customers in the EEA and Switzerland contract with Groq UK Limited.", "endpointOnVendorDomain": true, "terms": "https://console.groq.com/docs/legal/services-agreement", "privacy": "https://groq.com/privacy-policy", "statusPage": "https://groqstatus.com", "changelog": "https://console.groq.com/docs/changelog", "securityTxt": "valid", "checked": "2026-10-08", "score": 98 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/groq-speech-to-text.json", "live": { "slug": "groq-speech-to-text", "probe": { "target": "https://api.groq.com/openai/v1", "method": "get", "lastAt": "2026-11-07T18:20:28.965397134Z", "lastOk": true, "lastStatus": 404, "lastMs": 262, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 189, "p95ms24h": 289, "samples24h": 239, "samples30d": 7289, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 169 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://groqstatus.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:14.116118946Z" }, "versions": [ { "registry": "github", "name": "groq/groq-python", "version": "v1.7.0", "released": "2026-08-26", "seenAt": "2026-11-06T23:31:28.205199785Z" }, { "registry": "npm", "name": "groq-sdk", "version": "1.6.0", "seenAt": "2026-11-06T23:31:27.776856732Z" }, { "registry": "pypi", "name": "groq", "version": "1.7.0", "released": "2026-08-26", "seenAt": "2026-11-06T23:31:27.565009744Z" } ], "githubStars": 621, "npmWeekly": 1222883, "pypiWeekly": 4097095, "securityTxt": { "url": "https://groq.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-07T16:00:16.152471691Z" }, "llmsTxt": { "url": "https://console.groq.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:39.639791068Z" }, "domain": { "domain": "groq.com", "registered": "2007-07-22", "source": "https://rdap.verisign.com/com/v1/domain/groq.com", "checkedAt": "2026-11-01T14:20:57.072575938Z" }, "pages": [ { "url": "https://console.groq.com/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:01:55.345022013Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ac2cb86ef05a" }, { "url": "https://groq.com/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:10:41.745412878Z", "changedAt": "2026-10-09T18:39:59.465247347Z", "fingerprint": "1ae299b9f26b" }, { "url": "https://console.groq.com/docs/legal/services-agreement", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:01:59.94255172Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a0b93cf713d4" } ], "github": { "repo": "groq/groq-python", "checkedAt": "2026-11-02T08:53:10.526782877Z", "stars": 622, "archived": false, "issuesEnabled": false, "pushedAt": "2026-09-04T20:45:45Z", "openIssues": 0, "openPRs": 1, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 2, "ci": { "branch": "main", "runs": 41, "success": 31, "failure": 2, "other": 8, "latest": "skipped", "latestAt": "2026-09-04T20:45:23Z" } }, "updatedAt": "2026-11-07T18:21:14.116118946Z" } }, "answer": "Groq Speech-to-Text scores 70.1 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories.", "b": { "slug": "inworld-stt", "name": "Inworld STT", "vendor": "Inworld AI", "vendorUrl": "https://inworld.ai", "kind": "model", "category": "speech-to-text", "summary": "Inworld's speech-to-text API runs its `inworld/inworld-stt-1` model in 30 languages over synchronous HTTP, bidirectional WebSocket streaming and asynchronous jobs, returning Voice Profile signals (age, emotion, pitch, accent) and turn detection alongside the transcript.", "url": "https://www.anchorterminal.com/tools/inworld-stt", "markdownUrl": "https://www.anchorterminal.com/tools/inworld-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inworld-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inworld-stt.json", "dns": "inworld-stt.grade.anchorterminal.com", "transports": [ "http", "websocket" ], "packages": [ { "registry": "npm", "name": "@inworld/cli" } ], "auth": "api-key", "authNotes": "Every call sends `Authorization: Basic` with the Base64 `key_id:secret` credential from the Portal or the CLI. Keys belong to a workspace and are deleted to revoke. Browsers pass a one-time token in the `bearer_` WebSocket subprotocol rather than the URL.", "pricing": "usage", "pricingNotes": "$0.15 an hour of audio on the free On-Demand plan and $0.10 on the paid plans ($25 to $1,500 a month), billed per second. On-Demand includes up to 400 minutes free. Diarisation and Voice Profile are separate per-second add-ons. Asynchronous jobs need a payment method.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or pricing page (checked 2026-11-06). Plans and credits are bought in the Portal.", "endpoints": [] }, "toolCount": 0, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.inworld.ai/stt/overview", "llmsTxt": "https://docs.inworld.ai/llms.txt", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "tags": [ "hosted", "usage", "free-tier", "no-card", "closed-source", "llms-txt", "streaming", "batch", "mcp", "enterprise" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 54.7, "grade": "C", "agentReady": false, "rank": 895, "ranked": true, "rankOf": 1486, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 56, "maintenance": 41, "payments": 40, "reliability": 60, "schema": 54, "security": 63, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Inworld STT costs $0.10 to $0.15 an hour with 400 free minutes, and covers files, live streams and async jobs in 30 languages with Voice Profile signals. There is no machine-readable spec, no public STT changelog and no readable status history, and diarisation is still experimental.", "bestFor": "Low-cost live transcription for voice agents, with speaker traits.", "strengths": [ "$0.15 an hour on the free plan and $0.10 on paid plans, billed per second, with 400 free minutes", "Sync, WebSocket streaming and async jobs on one model, with turn detection and Voice Profile signals", "Browser tokens travel in a WebSocket subprotocol, not the URL", "Zero data retention keeps audio and transcripts in memory, and the docs include it from the Developer plan", "llms.txt, Markdown twins and a docs MCP server" ], "weaknesses": [ "No OpenAPI or other machine-readable contract", "The STT release notes path asks for a login, so changes to the model aren't publicly dated", "Status history couldn't be read, and an SLA exists only for Enterprise", "Speaker diarisation is experimental and async jobs run on a `v1alpha` operations route", "Docs and the STT product page disagree on which plans include zero data retention" ], "agentNotes": [ "Send the Base64 credential as-is in `Authorization: Basic`; don't encode it again", "Wrap the first WebSocket message in `transcribeConfig`, because a malformed first frame closes the socket with 1005 and no error", "Use `POST /stt/v1/transcribe:async` for files over about 16 MB and collect the transcript within 7 days", "Retry 429 or gRPC code 8 with exponential backoff and jitter, and stay within the plan's streaming concurrency", "Stop sending audio when nobody speaks, since streams are billed for every second sent" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.7 } ], "editorialScores": { "ergonomics": 56, "maintenance": 41, "payments": 40, "reliability": 60, "schema": 54, "security": 63, "transparency": 45 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @inworld/cli", "claudeCode": "claude mcp add inworld -- inworld mcp" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/inworld-stt" }, "sameCompany": [ "inworld-tts", "inworld-realtime", "inworld-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "STT-1, On-Demand", "unit": "audio-minute", "usd": 0.0025, "note": "$0.15 an hour" }, { "item": "STT-1, paid plans", "unit": "audio-minute", "usd": 0.00167, "note": "$0.10 an hour on Creator to Growth" } ], "provenance": { "legalEntity": "Theai, Inc. dba Inworld AI", "domain": "inworld.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://inworld.ai/terms", "privacy": "https://inworld.ai/privacy", "statusPage": "https://status.inworld.ai", "changelog": "https://docs.inworld.ai/release-notes/realtime", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The Terms of Service (effective 11 June 2025) are an agreement with Theai, Inc. dba Inworld AI under California law, with courts in Santa Clara. The Privacy Notice (last updated 18 January 2026) names Theai, Inc.", "inworld.ai/.well-known/security.txt returns 404. The security page links a vulnerability report form.", "status.inworld.ai runs the open-source issue-status app, which draws incidents from GitHub issues in inworld-ai/inworld-issue-status. Its history wasn't read, because GitHub's robots.txt couldn't be read from our environment.", "inworld.ai's robots.txt allows Claude agents on the paths read and sets `Content-Signal: ai-train=no, search=yes, ai-input=no`. docs.inworld.ai has no such signal.", "The domain's registration date wasn't established, because the RDAP lookup failed.", "firstReleased is left empty. No dated STT launch was found, and the STT release notes path asks for a Portal login." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inworld-stt.json", "live": { "slug": "inworld-stt", "versions": [ { "registry": "npm", "name": "@inworld/cli", "version": "1.5.0", "seenAt": "2026-11-06T23:35:05.474861108Z" } ], "npmWeekly": 290, "securityTxt": { "url": "https://inworld.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:11.794771951Z" }, "llmsTxt": { "url": "https://docs.inworld.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:47.741512787Z" }, "updatedAt": "2026-11-07T16:01:11.794771951Z" } }, "edges": [ { "by": 30, "category": "reliability", "leads": "groq-speech-to-text", "name": "Reliability", "reasons": { "a": "Hosted reading. The status page at groqstatus.com (incident.io) lists `whisper-large-v3` and `whisper-large-v3-turbo` as separate production components (20). On 1 November 2026 it showed both at 100% uptime from 3 August to 1 November with \"No incidents\", and neither its RSS feed nor the incident pages it links names either model. The window's three incidents were on other components (an enterprise preview model on 10 and 12 October, and console errors on 12 October that Groq said did not affect inference), plus maintenance on 9 and 18 October (30). The rate limits page gives numbers for both models, 20 requests a minute, 2,000 a day, 7,200 audio seconds an hour and 28,800 a day on the free plan, re-read on 1 November, and the models page gives 300 requests a minute and 200,000 audio seconds an hour (v3) and 400 and 400,000 (Turbo) on the Developer plan (15). A 429 carries `retry-after`, the security onboarding page says to back off exponentially on 429 and 5xx, and transcription is a stateless call (15). The enterprise Performance Tier's 99.9% availability SLA names three language models and neither Whisper model, per the 8 October check, so no SLA was found for this product (0). Both models are listed as production models (10). 20+30+15+15+0+10 = 90.", "b": "Hosted reading of the checklist. status.inworld.ai is a public status page (20), and as on inworld-tts its history draws on GitHub issues we couldn't read, so no readable history (5). Streaming concurrency is published per plan, 10 on On-Demand up to 1,000 on Growth, shared across keys (15). 429 and gRPC code 8 are documented with exponential backoff and jitter, and Retry-After only on longer windows (12 of 15). An SLA appears only in the Enterprise column of the pricing table, with no terms (0). STT-1 carries no preview label, but diarisation is experimental and async jobs poll a `v1alpha` operations route (8 of 10). 20 + 5 + 15 + 12 + 0 + 8 = 60." }, "scores": { "a": 90, "b": 60 } }, { "by": 25, "category": "transparency", "leads": "groq-speech-to-text", "name": "Transparency \u0026 trust", "reasons": { "a": "The hosted service is closed under the Groq Services Agreement. Both models are OpenAI's published Whisper weights, linked from each model card, served with Groq's own quantisation, and the SDKs are Apache-2.0 (20 of 30). The data page, the services agreement and the DPA agree on retention and on the training ban. The agreement limits zero retention to 'Eligible Customers' while the data page says all customers may enable it, and the privacy policy effective 12 November 2025 says it does not cover customer data sent to GroqCloud (26 of 30). A deprecations page with dated history and replacements, with no minimum notice period (14 of 20). Customer data is kept in Google Cloud storage in the United States, and the DPA gives 15 days' notice of sub-processor changes to subscribers. The sub-processor list is in the trust centre we could not read (12 of 20).", "b": "Closed service with clear terms naming Theai, Inc. dba Inworld AI (15). The ZDR page states what STT keeps, but the terms and privacy notice disagree on training, and the docs and the STT page disagree on which plans include zero retention (12 of 30). No dated STT deprecation or change notices are public (8 of 20). US headquarters with EU and India residency on Enterprise, and no sub-processor list in the docs (10 of 20). Total 45." }, "scores": { "a": 85, "b": 60 } }, { "by": 19, "category": "ergonomics", "leads": "groq-speech-to-text", "name": "Agent ergonomics", "reasons": { "a": "API reading, as for the other speech-to-text listings. The default response is the text alone, `text` returns a bare string, and segments and word timestamps come only with `verbose_json`. `srt` and `vtt` are listed as unsupported (18 of 25). There is no transcript store to page through. Volume goes through the Batch API by `url`, and a file over 25 MB (free) or 100 MB (Developer) has to be chunked by the caller (12 of 20). The errors page gives 13 status codes with a recovery line each and an error object of `message` and `type`, with no machine-readable code field (15 of 20). The call is stateless and safe to retry, and the SDKs retry connection errors, 408, 409, 429 and 5xx by default. No idempotency key exists or is needed (15 of 20). `model` and one of `file` or `url` are the only required fields, with official Python and TypeScript SDKs and OpenAI SDK compatibility (15).", "b": "API reading of the checklist. Voice Profile, word timestamps and diarisation are opt-in, and responses carry a `usage` block (18 of 25). No lists to page. Async jobs return an operation to poll (8 of 20). Errors carry a numeric gRPC code and message on both endpoints, but a malformed first message closes the socket with 1005 and no frame (12 of 20). Sync calls are stateless and async calls return an operation, with no idempotency key, and empty transcripts and add-ons are billed (10 of 20). A call needs a model, an encoding and the audio. No STT SDK was found, only the CLI and its MCP server and REST examples (8 of 15). Total 56." }, "scores": { "a": 75, "b": 56 } }, { "by": 16, "category": "security", "leads": "groq-speech-to-text", "name": "Security \u0026 auth", "reasons": { "a": "Model reading, scored like the GroqCloud listing. Bearer keys belong to one project, each project has its own rate limits per model, and the security onboarding page covers rotation and immediate revocation. No way to limit a key to the audio endpoints was found (26 of 30). The services agreement, last modified 22 June 2026, says Groq may not use inputs or outputs for training or fine-tuning unless the customer grants permission (20). Inputs and outputs are not retained by default, logs kept for reliability or abuse last up to 30 days, and the data page lists both audio endpoints as eligible for zero data retention, a setting in Data Controls (15). Usage data and request logs per project and a read-only Reader role. No audit log of administrative actions was found (10 of 15). security.txt on groq.com holds a Contact line only, with no expiry date. The DPA commits to SOC 2 Type II audits, and the trust centre at trust.groq.com is drawn by script and was not read (8 of 20).", "b": "Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Workspace API keys sent as Basic credentials, deleted to revoke, with separate keys per environment advised. The CLI mints read-only keys unless `--write` is given, but write toggles cover only the Voice and Router APIs, so no key is limited to one product. Browsers use short-lived tokens minted server side, via the `bearer_` WebSocket subprotocol, not the URL (25 of 30). The Terms (11 June 2025) say Inworld won't train generally available models on customers' non-public Materials, except feedback and flagged content, while the Privacy Notice (18 January 2026) lists training AI models among its uses, per the inworld-tts check of 4 November (12 of 20). Zero data retention keeps STT audio and transcripts in memory and out of logs, included on Developer ($300 a month) and above per the docs, while the STT page says Enterprise or a Growth add-on. Async results and audio go after 7 days, and no default period is given for logs (8 of 15). Usage is attributed per key and a Performance page shows errors and throttling (8 of 15). SOC 2 Type II and HIPAA claimed and a vulnerability report form, with no security.txt or bug bounty, per the 4 November reading (10 of 20). Total 63." }, "scores": { "a": 79, "b": 63 } }, { "by": 7, "category": "maintenance", "leads": "groq-speech-to-text", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading, as for the GroqCloud listing, counting changes to this listing's own models and endpoints, as the OpenAI listings read their own models and the AWS listings their own service models. No dated change to speech-to-text was found in 2026. The Python SDK 1.7.0 (tag 25 August, uploaded to PyPI on 26 August 2026 per the 8 October check) and TypeScript SDK 1.6.0 (25 August) add chat reasoning guidance, CI workflows and lock-file updates and leave the audio code untouched. The last SDK change to the transcription code was Python 1.2.0 on 18 April 2026. A release that doesn't change this service can't set the recency line in this run, as for the Azure Translator listing, and Muse Spark Open's 15 October preview is a chat model, counted on the GroqCloud listing. So no change within 180 days was found (0, was 20). The deprecations page promises an email and a named replacement and states no minimum notice. The one speech-to-text retirement on it is `distil-whisper-large-v3-en` on 23 August 2025, and the newest announcement is 24 August 2026, for Compound (4 of 12). Neither Whisper model was retired or renamed in the last 90 days (8 of 8). A dated docs changelog with a feed exists, its newest entry is 18 April and none of its entries concern speech-to-text (8 of 15). SDK issue replies not sampled (5 of 10). Official `groq` 1.7.0 on PyPI and `groq-sdk` 1.6.0 on npm, per the tags (15). CI, release automation and lock-file vulnerability fixes in 1.7.0 (8 of 10). 0+4+8+8+5+15+8 = 48.", "b": "Read as a model. No public STT changelog. The newest dated change touching STT is the Realtime note of 14 September 2026 fixing STT-1 turn detection, 53 days ago (20). The CLI, which carries the STT command and MCP tool, shipped 1.4.0 to 1.5.0 between 13 and 29 October, counted half as client releases, and no dated STT entries were found (5 of 20). Discord and support@inworld.ai, with no evidence of answers read (6 of 15). No official STT SDK; the CLI is current (5 of 15). CLI on npm under MIT, current, CI not read (5 of 10). Total 41." }, "scores": { "a": 48, "b": 41 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Groq", "b": "Inworld AI", "name": "Vendor" }, { "a": "https://api.groq.com/openai/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, websocket", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "not published", "b": "$0.0017 per minute of audio", "name": "Price for speech-to-text" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary hosted service under the Groq Services Agreement. The SDKs are Apache-2.0 and the Whisper weights are published by OpenAI on Hugging Face", "b": "none", "name": "Licence" }, { "a": "none", "b": "0", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-08-26", "b": "2026-10-29", "name": "Last release" }, { "a": "2026-06-22", "b": "2025-06-11", "name": "Terms last updated" }, { "a": "2025-11-12", "b": "2026-01-18", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "621 stars", "b": "none", "name": "Popularity" }, { "a": "3.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Groq Speech-to-Text scores 70.1 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Groq Speech-to-Text or Inworld STT?" }, { "answer": "Both need an API key.", "question": "Do Groq Speech-to-Text and Inworld STT need an API key?" }, { "answer": "Groq Speech-to-Text has a hosted endpoint at https://api.groq.com/openai/v1. No hosted endpoint is listed for Inworld STT.", "question": "Can an agent call Groq Speech-to-Text and Inworld STT without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 90 against 60", "Agent ergonomics, 75 against 56", "Security \u0026 auth, 79 against 63", "Maintenance \u0026 community, 48 against 41", "Transparency \u0026 trust, 85 against 60" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install" ], "goodFor": "Suited to cheap, fast transcription of recorded files in many languages, and to agents that already hold a Groq key or use an OpenAI-compatible client.", "slug": "groq-speech-to-text", "watchFor": "No streaming or realtime endpoint and no diarisation in the reviewed documentation" }, { "aheadOn": null, "also": null, "goodFor": "Low-cost live transcription for voice agents, with speaker traits.", "slug": "inworld-stt", "watchFor": "No OpenAPI or other machine-readable contract" } ], "history": { "groq-speech-to-text": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": -1.7, "from": 71.8, "fromGrade": "BB", "to": 70.1, "toGrade": "BB" } ], "inworld-stt": null }, "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-groq-speech-to-text.json", "title": "Amazon Transcribe vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-inworld-stt.json", "title": "Amazon Transcribe vs Inworld STT", "url": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-groq-speech-to-text.json", "title": "AssemblyAI Speech-to-Text (Universal) vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-inworld-stt.json", "title": "AssemblyAI Speech-to-Text (Universal) vs Inworld STT", "url": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-groq-speech-to-text.json", "title": "Azure AI Speech speech-to-text vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-inworld-stt.json", "title": "Azure AI Speech speech-to-text vs Inworld STT", "url": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-groq-speech-to-text.json", "title": "Cartesia Ink vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-inworld-stt.json", "title": "Cartesia Ink vs Inworld STT", "url": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/deepgram-stt-vs-groq-speech-to-text.json", "title": "Deepgram Speech-to-Text (Nova-3, Flux) vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/deepgram-stt-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/deepgram-stt-vs-inworld-stt.json", "title": "Deepgram Speech-to-Text (Nova-3, Flux) vs Inworld STT", "url": "https://www.anchorterminal.com/compare/deepgram-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-groq-speech-to-text.json", "title": "ElevenLabs Scribe Speech to Text API vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt.json", "title": "ElevenLabs Scribe Speech to Text API vs Inworld STT", "url": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/giggy-stt-vs-groq-speech-to-text.json", "title": "Giggy Speech to Text vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/giggy-stt-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/giggy-stt-vs-inworld-stt.json", "title": "Giggy Speech to Text vs Inworld STT", "url": "https://www.anchorterminal.com/compare/giggy-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-groq-speech-to-text.json", "title": "Gladia Speech-to-Text API + MCP vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-inworld-stt.json", "title": "Gladia Speech-to-Text API + MCP vs Inworld STT", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-groq-speech-to-text.json", "title": "Google Cloud Speech-to-Text vs Groq Speech-to-Text", "url": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-groq-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-inworld-stt.json", "title": "Google Cloud Speech-to-Text vs Inworld STT", "url": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-ibm-watson-stt.json", "title": "Groq Speech-to-Text vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-minimax-stt.json", "title": "Groq Speech-to-Text vs MiniMax Speech-to-Text", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-minimax-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-mistral-voxtral-transcribe.json", "title": "Groq Speech-to-Text vs Mistral Voxtral Transcribe", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-mistral-voxtral-transcribe" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-openai-speech-to-text.json", "title": "Groq Speech-to-Text vs OpenAI Speech to Text", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-openai-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-rev-ai-stt.json", "title": "Groq Speech-to-Text vs Rev AI Speech-to-Text API", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-rev-ai-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-smallest-pulse-stt.json", "title": "Groq Speech-to-Text vs Smallest.ai Pulse STT", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-smallest-pulse-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-soniox-stt.json", "title": "Groq Speech-to-Text vs Soniox Speech-to-Text", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-soniox-stt" }, { "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-speechmatics-stt.json", "title": "Groq Speech-to-Text vs Speechmatics Speech-to-Text", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-speechmatics-stt" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-inworld-stt.json", "title": "IBM Watson Speech to Text vs Inworld STT", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-inworld-stt" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-minimax-stt.json", "title": "Inworld STT vs MiniMax Speech-to-Text", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-minimax-stt" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-mistral-voxtral-transcribe.json", "title": "Inworld STT vs Mistral Voxtral Transcribe", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-mistral-voxtral-transcribe" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-openai-speech-to-text.json", "title": "Inworld STT vs OpenAI Speech to Text", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-openai-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-rev-ai-stt.json", "title": "Inworld STT vs Rev AI Speech-to-Text API", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-rev-ai-stt" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-smallest-pulse-stt.json", "title": "Inworld STT vs Smallest.ai Pulse STT", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-smallest-pulse-stt" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-soniox-stt.json", "title": "Inworld STT vs Soniox Speech-to-Text", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-soniox-stt" }, { "json": "https://www.anchorterminal.com/compare/inworld-stt-vs-speechmatics-stt.json", "title": "Inworld STT vs Speechmatics Speech-to-Text", "url": "https://www.anchorterminal.com/compare/inworld-stt-vs-speechmatics-stt" } ], "panel": null, "scores": [ { "by": 30, "edge": "groq-speech-to-text", "groq-speech-to-text": 90, "inworld-stt": 60, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "edge": "groq-speech-to-text", "groq-speech-to-text": 58, "inworld-stt": 54, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 19, "edge": "groq-speech-to-text", "groq-speech-to-text": 75, "inworld-stt": 56, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 16, "edge": "groq-speech-to-text", "groq-speech-to-text": 79, "inworld-stt": 63, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "groq-speech-to-text": 40, "inworld-stt": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "groq-speech-to-text", "groq-speech-to-text": 48, "inworld-stt": 41, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 25, "edge": "groq-speech-to-text", "groq-speech-to-text": 85, "inworld-stt": 60, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Groq Speech-to-Text scores 70.1 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories. Both do speech-to-text.", "tasks": [ { "a": "$0.04 to $0.11", "b": "$0.10 to $0.15", "cheaper": "groq-speech-to-text", "task": "Transcribe a one-hour meeting", "what": "60 minutes of recorded audio" } ], "tutorials": [], "verdicts": { "groq-speech-to-text": "Whisper Large v3 Turbo costs $0.04 an audio hour and Whisper Large v3 $0.111, with a no-card free plan and zero data retention as a self-serve setting. There is no streaming endpoint, no diarisation and no subtitle output, and uploads stop at 25 MB on the free plan and 100 MB on the Developer plan.", "inworld-stt": "Inworld STT costs $0.10 to $0.15 an hour with 400 free minutes, and covers files, live streams and async jobs in 30 languages with Voice Profile signals. There is no machine-readable spec, no public STT changelog and no readable status history, and diarisation is still experimental." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt", "json": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.min.md" }, "markdown": "Groq Speech-to-Text scores 70.1 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories. Both do speech-to-text.\n\n- Groq Speech-to-Text: grade BB, 70.1/100, rank #211 of 1486. Markdown https://www.anchorterminal.com/tools/groq-speech-to-text.md · JSON https://www.anchorterminal.com/api/v1/tools/groq-speech-to-text.json\n- Inworld STT: grade C, 54.7/100, rank #895 of 1486. Markdown https://www.anchorterminal.com/tools/inworld-stt.md · JSON https://www.anchorterminal.com/api/v1/tools/inworld-stt.json\n- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md\n- All 320 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md\n\n## Which one, for what\n\n### Groq Speech-to-Text (BB)\n\nGood for: Suited to cheap, fast transcription of recorded files in many languages, and to agents that already hold a Groq key or use an OpenAI-compatible client.\n\nAhead on:\n- Reliability, 90 against 60\n- Agent ergonomics, 75 against 56\n- Security \u0026 auth, 79 against 63\n- Maintenance \u0026 community, 48 against 41\n- Transparency \u0026 trust, 85 against 60\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: No streaming or realtime endpoint and no diarisation in the reviewed documentation\n\n### Inworld STT (C)\n\nGood for: Low-cost live transcription for voice agents, with speaker traits.\n\nWatch for: No OpenAPI or other machine-readable contract\n\n\n## Why the edge\n\n### Reliability: Groq Speech-to-Text +30\n\n- Groq Speech-to-Text (90): Hosted reading. The status page at groqstatus.com (incident.io) lists `whisper-large-v3` and `whisper-large-v3-turbo` as separate production components (20). On 1 November 2026 it showed both at 100% uptime from 3 August to 1 November with \"No incidents\", and neither its RSS feed nor the incident pages it links names either model. The window's three incidents were on other components (an enterprise preview model on 10 and 12 October, and console errors on 12 October that Groq said did not affect inference), plus maintenance on 9 and 18 October (30). The rate limits page gives numbers for both models, 20 requests a minute, 2,000 a day, 7,200 audio seconds an hour and 28,800 a day on the free plan, re-read on 1 November, and the models page gives 300 requests a minute and 200,000 audio seconds an hour (v3) and 400 and 400,000 (Turbo) on the Developer plan (15). A 429 carries `retry-after`, the security onboarding page says to back off exponentially on 429 and 5xx, and transcription is a stateless call (15). The enterprise Performance Tier's 99.9% availability SLA names three language models and neither Whisper model, per the 8 October check, so no SLA was found for this product (0). Both models are listed as production models (10). 20+30+15+15+0+10 = 90.\n- Inworld STT (60): Hosted reading of the checklist. status.inworld.ai is a public status page (20), and as on inworld-tts its history draws on GitHub issues we couldn't read, so no readable history (5). Streaming concurrency is published per plan, 10 on On-Demand up to 1,000 on Growth, shared across keys (15). 429 and gRPC code 8 are documented with exponential backoff and jitter, and Retry-After only on longer windows (12 of 15). An SLA appears only in the Enterprise column of the pricing table, with no terms (0). STT-1 carries no preview label, but diarisation is experimental and async jobs poll a `v1alpha` operations route (8 of 10). 20 + 5 + 15 + 12 + 0 + 8 = 60.\n\n### Transparency \u0026 trust: Groq Speech-to-Text +25\n\n- Groq Speech-to-Text (85): The hosted service is closed under the Groq Services Agreement. Both models are OpenAI's published Whisper weights, linked from each model card, served with Groq's own quantisation, and the SDKs are Apache-2.0 (20 of 30). The data page, the services agreement and the DPA agree on retention and on the training ban. The agreement limits zero retention to 'Eligible Customers' while the data page says all customers may enable it, and the privacy policy effective 12 November 2025 says it does not cover customer data sent to GroqCloud (26 of 30). A deprecations page with dated history and replacements, with no minimum notice period (14 of 20). Customer data is kept in Google Cloud storage in the United States, and the DPA gives 15 days' notice of sub-processor changes to subscribers. The sub-processor list is in the trust centre we could not read (12 of 20).\n- Inworld STT (60): Closed service with clear terms naming Theai, Inc. dba Inworld AI (15). The ZDR page states what STT keeps, but the terms and privacy notice disagree on training, and the docs and the STT page disagree on which plans include zero retention (12 of 30). No dated STT deprecation or change notices are public (8 of 20). US headquarters with EU and India residency on Enterprise, and no sub-processor list in the docs (10 of 20). Total 45.\n\n### Agent ergonomics: Groq Speech-to-Text +19\n\n- Groq Speech-to-Text (75): API reading, as for the other speech-to-text listings. The default response is the text alone, `text` returns a bare string, and segments and word timestamps come only with `verbose_json`. `srt` and `vtt` are listed as unsupported (18 of 25). There is no transcript store to page through. Volume goes through the Batch API by `url`, and a file over 25 MB (free) or 100 MB (Developer) has to be chunked by the caller (12 of 20). The errors page gives 13 status codes with a recovery line each and an error object of `message` and `type`, with no machine-readable code field (15 of 20). The call is stateless and safe to retry, and the SDKs retry connection errors, 408, 409, 429 and 5xx by default. No idempotency key exists or is needed (15 of 20). `model` and one of `file` or `url` are the only required fields, with official Python and TypeScript SDKs and OpenAI SDK compatibility (15).\n- Inworld STT (56): API reading of the checklist. Voice Profile, word timestamps and diarisation are opt-in, and responses carry a `usage` block (18 of 25). No lists to page. Async jobs return an operation to poll (8 of 20). Errors carry a numeric gRPC code and message on both endpoints, but a malformed first message closes the socket with 1005 and no frame (12 of 20). Sync calls are stateless and async calls return an operation, with no idempotency key, and empty transcripts and add-ons are billed (10 of 20). A call needs a model, an encoding and the audio. No STT SDK was found, only the CLI and its MCP server and REST examples (8 of 15). Total 56.\n\n### Security \u0026 auth: Groq Speech-to-Text +16\n\n- Groq Speech-to-Text (79): Model reading, scored like the GroqCloud listing. Bearer keys belong to one project, each project has its own rate limits per model, and the security onboarding page covers rotation and immediate revocation. No way to limit a key to the audio endpoints was found (26 of 30). The services agreement, last modified 22 June 2026, says Groq may not use inputs or outputs for training or fine-tuning unless the customer grants permission (20). Inputs and outputs are not retained by default, logs kept for reliability or abuse last up to 30 days, and the data page lists both audio endpoints as eligible for zero data retention, a setting in Data Controls (15). Usage data and request logs per project and a read-only Reader role. No audit log of administrative actions was found (10 of 15). security.txt on groq.com holds a Contact line only, with no expiry date. The DPA commits to SOC 2 Type II audits, and the trust centre at trust.groq.com is drawn by script and was not read (8 of 20).\n- Inworld STT (63): Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Workspace API keys sent as Basic credentials, deleted to revoke, with separate keys per environment advised. The CLI mints read-only keys unless `--write` is given, but write toggles cover only the Voice and Router APIs, so no key is limited to one product. Browsers use short-lived tokens minted server side, via the `bearer_` WebSocket subprotocol, not the URL (25 of 30). The Terms (11 June 2025) say Inworld won't train generally available models on customers' non-public Materials, except feedback and flagged content, while the Privacy Notice (18 January 2026) lists training AI models among its uses, per the inworld-tts check of 4 November (12 of 20). Zero data retention keeps STT audio and transcripts in memory and out of logs, included on Developer ($300 a month) and above per the docs, while the STT page says Enterprise or a Growth add-on. Async results and audio go after 7 days, and no default period is given for logs (8 of 15). Usage is attributed per key and a Performance page shows errors and throttling (8 of 15). SOC 2 Type II and HIPAA claimed and a vulnerability report form, with no security.txt or bug bounty, per the 4 November reading (10 of 20). Total 63.\n\n### Maintenance \u0026 community: Groq Speech-to-Text +7\n\n- Groq Speech-to-Text (48): Model reading, as for the GroqCloud listing, counting changes to this listing's own models and endpoints, as the OpenAI listings read their own models and the AWS listings their own service models. No dated change to speech-to-text was found in 2026. The Python SDK 1.7.0 (tag 25 August, uploaded to PyPI on 26 August 2026 per the 8 October check) and TypeScript SDK 1.6.0 (25 August) add chat reasoning guidance, CI workflows and lock-file updates and leave the audio code untouched. The last SDK change to the transcription code was Python 1.2.0 on 18 April 2026. A release that doesn't change this service can't set the recency line in this run, as for the Azure Translator listing, and Muse Spark Open's 15 October preview is a chat model, counted on the GroqCloud listing. So no change within 180 days was found (0, was 20). The deprecations page promises an email and a named replacement and states no minimum notice. The one speech-to-text retirement on it is `distil-whisper-large-v3-en` on 23 August 2025, and the newest announcement is 24 August 2026, for Compound (4 of 12). Neither Whisper model was retired or renamed in the last 90 days (8 of 8). A dated docs changelog with a feed exists, its newest entry is 18 April and none of its entries concern speech-to-text (8 of 15). SDK issue replies not sampled (5 of 10). Official `groq` 1.7.0 on PyPI and `groq-sdk` 1.6.0 on npm, per the tags (15). CI, release automation and lock-file vulnerability fixes in 1.7.0 (8 of 10). 0+4+8+8+5+15+8 = 48.\n- Inworld STT (41): Read as a model. No public STT changelog. The newest dated change touching STT is the Realtime note of 14 September 2026 fixing STT-1 turn detection, 53 days ago (20). The CLI, which carries the STT command and MCP tool, shipped 1.4.0 to 1.5.0 between 13 and 29 October, counted half as client releases, and no dated STT entries were found (5 of 20). Discord and support@inworld.ai, with no evidence of answers read (6 of 15). No official STT SDK; the CLI is current (5 of 15). CLI on npm under MIT, current, CI not read (5 of 10). Total 41.\n\n## Score by category\n\n| Category | Weight | Groq Speech-to-Text | Inworld STT | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 90 | 60 | Groq Speech-to-Text +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 58 | 54 | Groq Speech-to-Text +4 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 56 | Groq Speech-to-Text +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 79 | 63 | Groq Speech-to-Text +16 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 48 | 41 | Groq Speech-to-Text +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 85 | 60 | Groq Speech-to-Text +25 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **70.1 · BB** | **54.7 · C** | |\n\n## Facts side by side\n\n| Fact | Groq Speech-to-Text | Inworld STT |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Groq | Inworld AI |\n| Hosted endpoint | `https://api.groq.com/openai/v1` | no (local only) |\n| Transports | HTTP | HTTP, websocket |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| Price for speech-to-text | not published | $0.0017 per minute of audio |\n| x402 | no | no |\n| Licence | Proprietary hosted service under the Groq Services Agreement. The SDKs are Apache-2.0 and the Whisper weights are published by OpenAI on Hugging Face | none |\n| Tools exposed | none | 0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-08-26 | 2026-10-29 |\n| Terms last updated | 2026-06-22 | 2025-06-11 |\n| Privacy policy last updated | 2025-11-12 | 2026-01-18 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 621 stars | none |\n| Agent reviews | 3.5/5 (4) | none |\n\n## What the same task costs\n\n| Task | Groq Speech-to-Text | Inworld STT |\n| --- | --- | --- |\n| Transcribe a one-hour meeting | $0.04 to $0.11 | $0.10 to $0.15 |\n\n## How the scores have moved\n\n### Groq Speech-to-Text\n\n- -1.7 on 1 November 2026: correction\n\n### Inworld STT\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Groq Speech-to-Text.** Whisper Large v3 Turbo costs $0.04 an audio hour and Whisper Large v3 $0.111, with a no-card free plan and zero data retention as a self-serve setting. There is no streaming endpoint, no diarisation and no subtitle output, and uploads stop at 25 MB on the free plan and 100 MB on the Developer plan.\n\n**Inworld STT.** Inworld STT costs $0.10 to $0.15 an hour with 400 free minutes, and covers files, live streams and async jobs in 30 languages with Voice Profile signals. There is no machine-readable spec, no public STT changelog and no readable status history, and diarisation is still experimental.\n\n## Before you call either\n\n### Groq Speech-to-Text\n\n1. Send `whisper-large-v3-turbo` for transcription and `whisper-large-v3` for translation to English. The translations endpoint does not accept Turbo.\n2. Pass `url` instead of `file` for audio over 25 MB, and split anything over the plan's size limit into overlapping chunks before sending.\n3. Set `response_format` to `verbose_json` before asking for `timestamp_granularities[]`. Word timestamps add latency, segment timestamps do not.\n4. Every request is billed as at least 10 seconds of audio, so join very short clips where the task allows.\n5. Read `retry-after` on a 429 and back off. Audio limits count seconds an hour and a day as well as requests.\n\n### Inworld STT\n\n1. Send the Base64 credential as-is in `Authorization: Basic`; don't encode it again\n2. Wrap the first WebSocket message in `transcribeConfig`, because a malformed first frame closes the socket with 1005 and no error\n3. Use `POST /stt/v1/transcribe:async` for files over about 16 MB and collect the transcript within 7 days\n4. Retry 429 or gRPC code 8 with exponential backoff and jitter, and stay within the plan's streaming concurrency\n5. Stop sending audio when nobody speaks, since streams are billed for every second sent\n\n## Questions\n\n### Which is better for AI agents, Groq Speech-to-Text or Inworld STT?\n\nGroq Speech-to-Text scores 70.1 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories.\n\n### Do Groq Speech-to-Text and Inworld STT need an API key?\n\nBoth need an API key.\n\n### Can an agent call Groq Speech-to-Text and Inworld STT without installing anything?\n\nGroq Speech-to-Text has a hosted endpoint at https://api.groq.com/openai/v1. No hosted endpoint is listed for Inworld STT.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.json, and with the fewest tokens: https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"groq-speech-to-text\", \"b\": \"inworld-stt\"}`. From a terminal: `anchor compare groq-speech-to-text inworld-stt`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/groq-speech-to-text.json and https://www.anchorterminal.com/api/v1/tools/inworld-stt.json\n\n## Other comparisons with Groq Speech-to-Text or Inworld STT\n\n- [Amazon Transcribe vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/amazon-transcribe-vs-groq-speech-to-text.md)\n- [Amazon Transcribe vs Inworld STT](https://www.anchorterminal.com/compare/amazon-transcribe-vs-inworld-stt.md)\n- [AssemblyAI Speech-to-Text (Universal) vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/assemblyai-stt-vs-groq-speech-to-text.md)\n- [AssemblyAI Speech-to-Text (Universal) vs Inworld STT](https://www.anchorterminal.com/compare/assemblyai-stt-vs-inworld-stt.md)\n- [Azure AI Speech speech-to-text vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-groq-speech-to-text.md)\n- [Azure AI Speech speech-to-text vs Inworld STT](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-inworld-stt.md)\n- [Cartesia Ink vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-groq-speech-to-text.md)\n- [Cartesia Ink vs Inworld STT](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-inworld-stt.md)\n- [Deepgram Speech-to-Text (Nova-3, Flux) vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/deepgram-stt-vs-groq-speech-to-text.md)\n- [Deepgram Speech-to-Text (Nova-3, Flux) vs Inworld STT](https://www.anchorterminal.com/compare/deepgram-stt-vs-inworld-stt.md)\n- [ElevenLabs Scribe Speech to Text API vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-groq-speech-to-text.md)\n- [ElevenLabs Scribe Speech to Text API vs Inworld STT](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt.md)\n- [Giggy Speech to Text vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/giggy-stt-vs-groq-speech-to-text.md)\n- [Giggy Speech to Text vs Inworld STT](https://www.anchorterminal.com/compare/giggy-stt-vs-inworld-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/gladia-stt-vs-groq-speech-to-text.md)\n- [Gladia Speech-to-Text API + MCP vs Inworld STT](https://www.anchorterminal.com/compare/gladia-stt-vs-inworld-stt.md)\n- [Google Cloud Speech-to-Text vs Groq Speech-to-Text](https://www.anchorterminal.com/compare/google-speech-to-text-vs-groq-speech-to-text.md)\n- [Google Cloud Speech-to-Text vs Inworld STT](https://www.anchorterminal.com/compare/google-speech-to-text-vs-inworld-stt.md)\n- [Groq Speech-to-Text vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-ibm-watson-stt.md)\n- [Groq Speech-to-Text vs MiniMax Speech-to-Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-minimax-stt.md)\n- [Groq Speech-to-Text vs Mistral Voxtral Transcribe](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-mistral-voxtral-transcribe.md)\n- [Groq Speech-to-Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-openai-speech-to-text.md)\n- [Groq Speech-to-Text vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-rev-ai-stt.md)\n- [Groq Speech-to-Text vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-smallest-pulse-stt.md)\n- [Groq Speech-to-Text vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-soniox-stt.md)\n- [Groq Speech-to-Text vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-speechmatics-stt.md)\n- [IBM Watson Speech to Text vs Inworld STT](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-inworld-stt.md)\n- [Inworld STT vs MiniMax Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-minimax-stt.md)\n- [Inworld STT vs Mistral Voxtral Transcribe](https://www.anchorterminal.com/compare/inworld-stt-vs-mistral-voxtral-transcribe.md)\n- [Inworld STT vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/inworld-stt-vs-openai-speech-to-text.md)\n- [Inworld STT vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/inworld-stt-vs-rev-ai-stt.md)\n- [Inworld STT vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/inworld-stt-vs-smallest-pulse-stt.md)\n- [Inworld STT vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-soniox-stt.md)\n- [Inworld STT vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-speechmatics-stt.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Groq Speech-to-Text vs Inworld STT", "url": "" } ], "description": "Groq Speech-to-Text scores 70.1 (BB) to Inworld STT's 54.7 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Groq Speech-to-Text BB 70.1", "Inworld STT C 54.7", "scores" ], "h1": "Groq Speech-to-Text vs Inworld STT", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/groq-speech-to-text-vs-inworld-stt", "published": "2026-10-01", "section": "tools", "title": "Groq Speech-to-Text vs Inworld STT for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt" }, "tokens": { "markdown": 5450, "slim": 3080 }, "version": 1 }