{ "data": { "a": { "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", "dns": "gladia-stt.grade.anchorterminal.com", "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, priced in euros. Self-serve async is 0.27€ an hour on `solaria-1` and 0.16€ on `solaria-3` for the first 100 hours a month, falling with volume to 0.21€ and 0.12€ above 10,000 hours. Real-time is 0.68€ an hour. Add-ons are billed per hour (summarisation 0.03€, sentiment 0.02€, translation 0.05€, NER and PII redaction 0.07€). Top-ups from 1,000€ earn 10 to 20 per cent bonus credit. New accounts get 50€ of free credit. Enterprise is custom (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": "2026-10-23", "graded": true, "anchor": { "graded": true, "score": 69.8, "grade": "B", "agentReady": false, "rank": 225, "ranked": true, "rankOf": 1486, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 70, "payments": 40, "reliability": 70, "schema": 95, "security": 65, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "The `solaria-1` model transcribes live and recorded audio in over 100 languages with code switching, behind an OpenAPI file and SDKs in two languages. Self-serve audio is used for model training unless the account opts out, and Gladia's pages disagree on retention and training defaults.", "bestFor": "Multilingual meetings and calls where live and async transcription in 100+ languages is needed, and for teams who want an MCP server.", "strengths": [ "100+ languages on `solaria-1` with code switching, live and async", "Async from 0.16€ an hour on `solaria-3`, with automatic volume discounts", "OpenAPI file, llms.txt, JavaScript and Python SDKs at 2.2.1 and an official MCP server", "SOC 2 Type 1 and Type 2, a bug bounty programme and a 99.9% uptime SLA on Enterprise", "One-time 50€ credit for new accounts" ], "weaknesses": [ "Self-serve audio is used for model training by default unless the account opts out", "The security, retention and pricing pages give different retention and training defaults", "Add-ons such as translation, summaries and NER now cost extra per hour", "ISO 27001 is still in progress", "No Retry-After on 429s, and no SLA below Enterprise" ], "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", "Opt the account out of model training in its profile before sending sensitive audio on Self-serve", "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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.8 } ], "editorialScores": { "ergonomics": 75, "maintenance": 70, "payments": 40, "reliability": 70, "schema": 95, "security": 65, "transparency": 50 }, "provenanceScore": 80, "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": { "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", "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": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gladia-stt.json", "live": { "slug": "gladia-stt", "probe": { "target": "https://api.gladia.io/v2", "method": "get", "lastAt": "2026-11-07T18:20:27.370683403Z", "lastOk": true, "lastStatus": 404, "lastMs": 477, "authRequired": false, "uptime24h": 100, "uptime30d": 99.9, "p50ms24h": 509, "p95ms24h": 946, "samples24h": 239, "samples30d": 7910, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 266 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "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": 248 }, { "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": 184 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ], "outages": [ { "start": "2026-10-07T12:49:45.159769611Z", "end": "2026-10-07T13:21:50.310567918Z", "note": "timed out" } ] }, "vendorStatus": { "page": "https://status.gladia.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:12.974903461Z" }, "versions": [ { "registry": "github", "name": "gladiaio/sdk", "version": "sdk-js@2.2.1", "released": "2026-10-23", "seenAt": "2026-11-06T23:28:32.463167469Z" }, { "registry": "npm", "name": "@gladiaio/mcp", "version": "0.1.1", "seenAt": "2026-11-06T23:28:30.94784336Z" }, { "registry": "npm", "name": "@gladiaio/sdk", "version": "2.2.1", "seenAt": "2026-11-06T23:28:30.257061478Z" }, { "registry": "pypi", "name": "gladiaio-sdk", "version": "2.2.1", "released": "2026-10-23", "seenAt": "2026-11-06T23:28:30.62979826Z" } ], "githubStars": 4, "npmWeekly": 9911, "pypiWeekly": 158166, "securityTxt": { "url": "https://gladia.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:36.428238118Z" }, "llmsTxt": { "url": "https://docs.gladia.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:35.899309498Z" }, "domain": { "domain": "gladia.io", "checkedAt": "2026-11-01T14:18:24.128393611Z" }, "pages": [ { "url": "https://www.gladia.io/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:29:13.022879231Z", "changedAt": "2026-10-31T06:27:50.8188043Z", "fingerprint": "2d9a97e569dd" }, { "url": "https://www.gladia.io/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:29:15.16091754Z", "changedAt": "2026-11-04T08:40:32.021344895Z", "fingerprint": "0ceaa29762d7" }, { "url": "https://www.gladia.io/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:29:17.167728212Z", "changedAt": "2026-10-31T06:27:54.847451002Z", "fingerprint": "f9ff7892ae9b" }, { "url": "https://www.gladia.io/terms-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:29:19.407410784Z", "changedAt": "2026-10-31T06:27:56.886711706Z", "fingerprint": "a8aaf82e03a4" } ], "github": { "repo": "gladiaio/sdk", "checkedAt": "2026-11-02T08:50:58.697165055Z", "stars": 4, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T14:44:22Z", "openIssues": 5, "openPRs": 1, "issuesOpened90d": 2, "issuesClosed90d": 2, "prsMerged90d": 20, "replies": { "sampled": 9, "unanswered": 5, "medianDays": 1.6 } }, "updatedAt": "2026-11-07T18:21:12.974903461Z" } }, "answer": "Gladia Speech-to-Text API + MCP scores 69.8 (B) on agent readiness against IBM Watson Speech to Text's 54.5 (C), and leads in 4 of 7 scored categories. IBM Watson Speech to Text leads on transparency \u0026 trust.", "b": { "slug": "ibm-watson-stt", "name": "IBM Watson Speech to Text", "vendor": "IBM", "vendorUrl": "https://www.ibm.com/products/speech-to-text", "kind": "model", "category": "speech-to-text", "summary": "IBM Watson Speech to Text transcribes audio over synchronous and asynchronous HTTP and a WebSocket interface on IBM Cloud, with large speech models, next-generation models, custom language and acoustic models, speaker labels and language identification.", "url": "https://www.anchorterminal.com/tools/ibm-watson-stt", "markdownUrl": "https://www.anchorterminal.com/tools/ibm-watson-stt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ibm-watson-stt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ibm-watson-stt.json", "dns": "ibm-watson-stt.grade.anchorterminal.com", "transports": [ "http", "websocket" ], "packages": [ { "registry": "pypi", "name": "ibm-watson" }, { "registry": "npm", "name": "ibm-watson" } ], "auth": "api-key", "authNotes": "An IBM Cloud IAM API key per service instance, exchanged for a bearer token or sent with Basic auth as `apikey:\u003ckey\u003e`. Service credentials carry IAM roles. The WebSocket interface takes the IAM token as an `access_token` query parameter.", "pricing": "freemium", "pricingNotes": "Lite plan free for 500 minutes a month, deleted after 30 days of inactivity. Plus plan $0.02 a minute up to 999,999 minutes a month and $0.01 above, with up to 100 concurrent requests. Premium by quote.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or API reference (checked 2026-11-06). Billing runs through an IBM Cloud account.", "endpoints": [] }, "toolCount": 0, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://cloud.ibm.com/docs/speech-to-text", "capabilities": [ "speech.stt", "speech.streaming", "speech.batch", "speech.diarisation", "speech.languages" ], "tags": [ "hosted", "freemium", "closed-source", "python", "typescript", "enterprise", "streaming", "batch", "async-jobs", "webhooks" ], "lastRelease": "2026-06-29", "graded": true, "anchor": { "graded": true, "score": 54.5, "grade": "C", "agentReady": false, "rank": 904, "ranked": true, "rankOf": 1486, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 33, "payments": 40, "reliability": 40, "schema": 55, "security": 68, "transparency": 80 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Watson STT covers sync, async and WebSocket transcription in ten locations, with custom models, $0.02 a minute on Plus and 500 free minutes. There is no machine-readable spec or readable status history, requests are logged for improvement unless opted out, the WebSocket token goes in the URL, and the last release note is from June 2026.", "bestFor": "Enterprises on IBM Cloud needing custom acoustic models, HIPAA on Premium and many locations.", "strengths": [ "Sync, async with callbacks and WebSocket streaming on one service", "500 free minutes a month on Lite and $0.02 a minute on Plus", "Custom language and acoustic models on paid plans", "Dated deprecation of previous-generation models with over a year of notice", "`DELETE /v1/user_data` removes data by customer ID" ], "weaknesses": [ "No public OpenAPI file or llms.txt", "The WebSocket interface takes the IAM token as a URL query parameter", "Requests are logged by default to improve the service unless the account or request opts out", "The status page is drawn by script and no SLA was read", "No release note since 29 June 2026" ], "agentNotes": [ "Send `X-Watson-Learning-Opt-Out: true` or opt out at account level before sending sensitive audio", "Use the async `/v1/recognitions` interface with a callback for files over 100 MB, up to 1 GB", "Pass a large speech or next-generation model name in `model`, since previous-generation models were removed", "Tag requests with `X-Watson-Metadata: customer_id=...` so the data can be deleted later", "Keep within 100 concurrent requests on Plus across HTTP and WebSocket" ], "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": 54.5 } ], "editorialScores": { "ergonomics": 66, "maintenance": 33, "payments": 40, "reliability": 40, "schema": 55, "security": 68, "transparency": 65 }, "provenanceScore": 94, "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": "pip install ibm-watson" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/ibm-watson-stt" }, "sameCompany": [ "granite-embedding-small-english-r2", "granite-guardian", "granite-switch", "granite-4-2-3b" ], "area": "voice", "unitPrices": [ { "item": "Plus plan, first 999,999 minutes a month", "unit": "audio-minute", "usd": 0.02 }, { "item": "Plus plan, from 1,000,000 minutes a month", "unit": "audio-minute", "usd": 0.01 } ], "provenance": { "legalEntity": "International Business Machines Corporation", "domain": "ibm.com", "domainRegistered": "1986-03-19", "domainNote": "The endpoints are on watson.cloud.ibm.com, under ibm.com.", "endpointOnVendorDomain": true, "terms": "https://cloud.ibm.com/docs/overview?topic=overview-terms", "privacy": "https://www.ibm.com/privacy", "statusPage": "https://cloud.ibm.com/status", "changelog": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-release-notes", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "cloud.ibm.com/robots.txt disallows only /docs/search?q= and sets Content-Signal ai-train=yes, search=yes, ai-input=yes.", "www.ibm.com/.well-known/security.txt names IBM PSIRT, HackerOne and psirt@us.ibm.com and expires on 6 December 2026.", "cloud.ibm.com/status returns a page drawn by script, so its incident history wasn't read.", "The IBM Cloud terms page was found but its text wasn't read, so no clause is quoted.", "RDAP gives ibm.com a registration date of 19 March 1986." ], "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ibm-watson-stt.json", "live": { "slug": "ibm-watson-stt", "vendorStatus": { "page": "https://cloud.ibm.com/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:55.897466786Z" }, "versions": [ { "registry": "npm", "name": "ibm-watson", "version": "12.2.0", "seenAt": "2026-11-06T23:34:06.712780272Z" }, { "registry": "pypi", "name": "ibm-watson", "version": "11.2.0", "released": "2026-01-26", "seenAt": "2026-11-06T23:34:06.544738844Z" } ], "npmWeekly": 12367, "pypiWeekly": 10209, "securityTxt": { "url": "https://ibm.com/.well-known/security.txt", "state": "valid", "expires": "2026-12-07T00:00:00+00:00", "checkedAt": "2026-11-07T16:00:08.596796331Z" }, "pages": [ { "url": "https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:01:17.694727718Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8dcf87213e78" }, { "url": "https://www.ibm.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:30:01.132495816Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "cf480cd7bcca" }, { "url": "https://cloud.ibm.com/docs/overview?topic=overview-terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:01:13.338724324Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a0514cb0ed80" } ], "updatedAt": "2026-11-07T16:00:08.596796331Z" } }, "edges": [ { "by": 40, "category": "schema", "leads": "gladia-stt", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI file at api.gladia.io/openapi.json (25). llms.txt (10). Reference pages state purpose per endpoint and the model page says to use `solaria-3` only for async English, French, German, Spanish or Italian (15). Typed bodies with enums and required fields, `audio_url` the only required input for pre-recorded (15). Examples per endpoint and documented error codes (15). Versioned `/v2` paths and a dated changelog (15).", "b": "No public OpenAPI or other machine-readable definition was found (0). No llms.txt (0). The reference says which parameters each model family supports and the docs cover each feature (15 of 20). Typed parameters with defaults, ranges and enums (13 of 15). curl and SDK examples on every method, and errors with `error`, `code`, `code_description` and `warnings`, with invalid arguments reported as warnings (12 of 15). Versioned `/v1` paths and dated release notes back to 2015 (15). Total 55." }, "scores": { "a": 95, "b": 55 } }, { "by": 37, "category": "maintenance", "leads": "gladia-stt", "name": "Maintenance \u0026 community", "reasons": { "a": "Read as a model, for deprecation notice and model churn rather than release counts, on the lines deepgram-stt was settled on in this run. SDK 2.2.0 on 13 October 2026, three fixes among them limiting list pagination to the configured API, 19 days before 1 November (30). 2.2.1 on 23 October only raises the Python `certifi` floor to distrust a compromised certificate authority and is a version bump with no code changes for JavaScript, so as a dependency-only release it counts half and doesn't set this line, as azure-translator's was read. In the 90 days from 3 August, changelog entries on 8, 9 and 14 September, SDK 2.1.0 (18 and 21 September), 2.2.0 and 2.2.1 (at half), and the MCP server 0.1.0 and 0.1.1 on 24 September (10). The `/v2/transcription` endpoints are marked deprecated in favour of `/v2/pre-recorded` with no removal date, structured data extraction has gone from the OpenAPI file without a changelog entry, and no deprecation policy was found (0 of 10). Public changelog, help centre and Discord (10 of 15). SDK and MCP repository issues couldn't be read, since github.com refuses our reader, so absent (0 of 10). Official JavaScript and Python SDKs current at 2.2.1 (15). The SDK repository has CI, release and OpenAPI type-update workflows, results not seen (5 of 10). 30 + 10 + 0 + 10 + 0 + 15 + 5 = 70.", "b": "Read as a model. The newest release note is 29 June 2026 (`parameter_set` for large speech models), 130 days ago (10). No dated entries in the 90 days from 8 August (0). Release notes, IBM support and a public docs repository last changed 30 June 2026 (8 of 15). Official SDKs, `ibm-watson` 11.2.0 on PyPI (26 January 2026) and 12.2.0 on npm (January 2026) (10 of 15). CI not read (5 of 10). Total 33." }, "scores": { "a": 70, "b": 33 } }, { "by": 30, "category": "reliability", "leads": "gladia-stt", "name": "Reliability", "reasons": { "a": "incident.io status page with per-component uptime bars and incident pages, and an RSS feed read on 1 November (20). One major incident in the 90 days from 3 August, a global Pre-Recorded and Real-Time incident on 23 September 2026 from 07:05 to 08:10 caused by a provider network fault, as read on 1 October. The rest are partial and read as minor, a 20-minute full outage and a timeouts incident on 22 September, slower processing on the afternoon of 23 September, and Europe-only degradations on 2, 10, 14 to 15 (elevated errors and timeouts in Europe from 09:07 on 14 September to 13:58 on 15 September), 21, 22 and 28 September and on 3, 4 and 7 October (Pre-Recorded v2 in Europe) (10). Concurrency limits published with numbers, 25 parallel async jobs plus 300 queued and 30 live sessions on paid plans, 3 and 1 on free (15). The docs say a 429 means the concurrency limit, but we found no backoff guidance or Retry-After (5). The pricing page's plan comparison, read on 1 November, lists a 99.9% uptime SLA for Enterprise (10). `solaria-1` and `solaria-3` are GA (10). 20 + 10 + 15 + 5 + 10 + 10 = 70.", "b": "IBM Cloud has a status page at cloud.ibm.com/status, but it is drawn by script and showed no components or history to our reader, read as gemini-live's script-shell page was (10 of 20, and 5 for no readable history). Plus allows up to 100 concurrent transcription requests across WebSocket and HTTP (15). No 429 or backoff guidance was found in the API reference or the docs repository (0). No SLA was read for the service (0, unchecked). Next-generation and large speech models are GA, language by language (10). 10 + 5 + 15 + 0 + 0 + 10 = 40." }, "scores": { "a": 70, "b": 40 } }, { "by": 15, "category": "transparency", "leads": "ibm-watson-stt", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service with an MIT SDK and MCP server and separate terms for Gladia SAS and Gladia Inc. (15). The statements disagree. The security page gives a 12-month default retention with custom policies for customers and says only Free plan data trains models, while the retention page gives 1 year on free, 3 weeks on paid and zero retention only on Enterprise, and the pricing page says Self-serve is opted in to training by default. ISO 27001 is described as in progress (15). Breaking changes are flagged with dates in the changelog, such as SDK 2.0.0 and the move to credit billing on 3 July 2026 with a 6 to 20 July rollout, but no deprecation policy was found (10). Hosting with a French provider is stated, and no sub-processor list was found (10).", "b": "Closed service under the IBM Cloud terms (15). The data security page states default logging for improvement with an opt-out, async retention, GDPR deletion by customer ID and plan-level separation, and they agree with each other. The DPA wasn't read (20 of 30). Previous-generation models carried a dated deprecation of 15 March 2022 and removal on 31 July 2023, and release notes say changes are compatible unless noted (18 of 20). Ten locations are named, with sub-processors not read (12 of 20). Total 65." }, "scores": { "a": 65, "b": 80 } }, { "by": 9, "category": "ergonomics", "leads": "gladia-stt", "name": "Agent ergonomics", "reasons": { "a": "API reading of the checklist. Add-ons such as summaries, NER and translation are opt-in, so a plain request stays small, but there's no field selection (15). Pre-recorded jobs list with offset, limit and filters (20). Documented error codes, with a 429 for concurrency (15). No idempotency key. The docs warn that a job is already queued once the 200 or `transcription.created` webhook arrives, which is safe-retry guidance of a sort (10). One required parameter and official SDKs in JavaScript and Python (15). The official MCP server adds 8 tools for async jobs, which this API reading doesn't score.", "b": "API reading of the checklist. Timestamps, word confidence, alternatives and speaker labels are opt-in (15 of 25). Async jobs and custom models list, and async results can go to a callback URL (12 of 20). Structured errors and warnings an agent can act on (15 of 20). Async jobs take a `user_token`, results have a TTL, and jobs can be deleted, with no idempotency key (12 of 20). Most parameters are optional. Official SDKs including Python, Node and Swift, though the Python and Node SDKs last released in January 2026 (12 of 15). Total 66." }, "scores": { "a": 75, "b": 66 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Gladia", "b": "IBM", "name": "Vendor" }, { "a": "https://api.gladia.io/v2", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP, websocket", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT (SDKs and MCP server)", "b": "none", "name": "Licence" }, { "a": "8", "b": "0", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-23", "b": "2026-06-29", "name": "Last release" }, { "a": "no date given", "b": "no date given", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-08-25", "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": "not found in the text", "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": "4 stars, 4.8k npm/wk, 126k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Gladia Speech-to-Text API + MCP scores 69.8 (B) on agent readiness against IBM Watson Speech to Text's 54.5 (C), and leads in 4 of 7 scored categories. IBM Watson Speech to Text leads on transparency \u0026 trust.", "question": "Which is better for AI agents, Gladia Speech-to-Text API + MCP or IBM Watson Speech to Text?" }, { "answer": "Both need an API key.", "question": "Do Gladia Speech-to-Text API + MCP and IBM Watson Speech to Text need an API key?" }, { "answer": "Gladia Speech-to-Text API + MCP has a hosted endpoint at https://api.gladia.io/v2. No hosted endpoint is listed for IBM Watson Speech to Text.", "question": "Can an agent call Gladia Speech-to-Text API + MCP and IBM Watson Speech to Text without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 40", "Schema \u0026 documentation, 95 against 55", "Agent ergonomics, 75 against 66", "Maintenance \u0026 community, 70 against 33" ], "also": [ "A hosted endpoint, with nothing to install", "Runs on your own machine", "Free to start without a card" ], "goodFor": "Multilingual meetings and calls where live and async transcription in 100+ languages is needed, and for teams who want an MCP server.", "slug": "gladia-stt", "watchFor": "Self-serve audio is used for model training by default unless the account opts out" }, { "aheadOn": [ "Transparency \u0026 trust, 80 against 65" ], "also": null, "goodFor": "Enterprises on IBM Cloud needing custom acoustic models, HIPAA on Premium and many locations.", "slug": "ibm-watson-stt", "watchFor": "No public OpenAPI file or llms.txt" } ], "history": { "gladia-stt": [ { "causes": [ "terms", "correction" ], "date": "2026-11-01", "delta": 0.2, "from": 69.6, "fromGrade": "B", "to": 69.8, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 69.5, "fromGrade": "B", "to": 69.6, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.2, "from": 69.7, "fromGrade": "B", "to": 69.5, "toGrade": "B" } ], "ibm-watson-stt": null }, "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-gladia-stt.json", "title": "Amazon Transcribe vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-ibm-watson-stt.json", "title": "Amazon Transcribe vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/amazon-transcribe-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-gladia-stt.json", "title": "AssemblyAI Speech-to-Text (Universal) vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-ibm-watson-stt.json", "title": "AssemblyAI Speech-to-Text (Universal) vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/assemblyai-stt-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-gladia-stt.json", "title": "Azure AI Speech speech-to-text vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-ibm-watson-stt.json", "title": "Azure AI Speech speech-to-text vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/azure-speech-to-text-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-gladia-stt.json", "title": "Cartesia Ink vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-ibm-watson-stt.json", "title": "Cartesia Ink vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/deepgram-stt-vs-gladia-stt.json", "title": "Deepgram Speech-to-Text (Nova-3, Flux) vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-stt-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/deepgram-stt-vs-ibm-watson-stt.json", "title": "Deepgram Speech-to-Text (Nova-3, Flux) vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/deepgram-stt-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-gladia-stt.json", "title": "ElevenLabs Scribe Speech to Text API vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-ibm-watson-stt.json", "title": "ElevenLabs Scribe Speech to Text API vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/giggy-stt-vs-gladia-stt.json", "title": "Giggy Speech to Text vs Gladia Speech-to-Text API + MCP", "url": "https://www.anchorterminal.com/compare/giggy-stt-vs-gladia-stt" }, { "json": "https://www.anchorterminal.com/compare/giggy-stt-vs-ibm-watson-stt.json", "title": "Giggy Speech to Text vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/giggy-stt-vs-ibm-watson-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-google-speech-to-text.json", "title": "Gladia Speech-to-Text API + MCP vs Google Cloud Speech-to-Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-google-speech-to-text" }, { "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/gladia-stt-vs-minimax-stt.json", "title": "Gladia Speech-to-Text API + MCP vs MiniMax Speech-to-Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-minimax-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-mistral-voxtral-transcribe.json", "title": "Gladia Speech-to-Text API + MCP vs Mistral Voxtral Transcribe", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-mistral-voxtral-transcribe" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-openai-speech-to-text.json", "title": "Gladia Speech-to-Text API + MCP vs OpenAI Speech to Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-openai-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-rev-ai-stt.json", "title": "Gladia Speech-to-Text API + MCP vs Rev AI Speech-to-Text API", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-rev-ai-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-smallest-pulse-stt.json", "title": "Gladia Speech-to-Text API + MCP vs Smallest.ai Pulse STT", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-smallest-pulse-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-soniox-stt.json", "title": "Gladia Speech-to-Text API + MCP vs Soniox Speech-to-Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-soniox-stt" }, { "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-speechmatics-stt.json", "title": "Gladia Speech-to-Text API + MCP vs Speechmatics Speech-to-Text", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-speechmatics-stt" }, { "json": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-ibm-watson-stt.json", "title": "Google Cloud Speech-to-Text vs IBM Watson Speech to Text", "url": "https://www.anchorterminal.com/compare/google-speech-to-text-vs-ibm-watson-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/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/ibm-watson-stt-vs-minimax-stt.json", "title": "IBM Watson Speech to Text vs MiniMax Speech-to-Text", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-minimax-stt" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-mistral-voxtral-transcribe.json", "title": "IBM Watson Speech to Text vs Mistral Voxtral Transcribe", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-mistral-voxtral-transcribe" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-openai-speech-to-text.json", "title": "IBM Watson Speech to Text vs OpenAI Speech to Text", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-openai-speech-to-text" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-rev-ai-stt.json", "title": "IBM Watson Speech to Text vs Rev AI Speech-to-Text API", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-rev-ai-stt" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-smallest-pulse-stt.json", "title": "IBM Watson Speech to Text vs Smallest.ai Pulse STT", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-smallest-pulse-stt" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-soniox-stt.json", "title": "IBM Watson Speech to Text vs Soniox Speech-to-Text", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-soniox-stt" }, { "json": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-speechmatics-stt.json", "title": "IBM Watson Speech to Text vs Speechmatics Speech-to-Text", "url": "https://www.anchorterminal.com/compare/ibm-watson-stt-vs-speechmatics-stt" } ], "panel": null, "scores": [ { "by": 30, "edge": "gladia-stt", "gladia-stt": 70, "ibm-watson-stt": 40, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 40, "edge": "gladia-stt", "gladia-stt": 95, "ibm-watson-stt": 55, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 9, "edge": "gladia-stt", "gladia-stt": 75, "ibm-watson-stt": 66, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 3, "edge": "ibm-watson-stt", "gladia-stt": 65, "ibm-watson-stt": 68, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "gladia-stt": 40, "ibm-watson-stt": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 37, "edge": "gladia-stt", "gladia-stt": 70, "ibm-watson-stt": 33, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 15, "edge": "ibm-watson-stt", "gladia-stt": 65, "ibm-watson-stt": 80, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Gladia Speech-to-Text API + MCP scores 69.8 (B) on agent readiness against IBM Watson Speech to Text's 54.5 (C), and leads in 4 of 7 scored categories. IBM Watson Speech to Text leads on transparency \u0026 trust. Both do speech-to-text.", "tasks": null, "tutorials": [], "verdicts": { "gladia-stt": "The `solaria-1` model transcribes live and recorded audio in over 100 languages with code switching, behind an OpenAPI file and SDKs in two languages. Self-serve audio is used for model training unless the account opts out, and Gladia's pages disagree on retention and training defaults.", "ibm-watson-stt": "Watson STT covers sync, async and WebSocket transcription in ten locations, with custom models, $0.02 a minute on Plus and 500 free minutes. There is no machine-readable spec or readable status history, requests are logged for improvement unless opted out, the WebSocket token goes in the URL, and the last release note is from June 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt", "json": "https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt.min.md" }, "markdown": "Gladia Speech-to-Text API + MCP scores 69.8 (B) on agent readiness against IBM Watson Speech to Text's 54.5 (C), and leads in 4 of 7 scored categories. IBM Watson Speech to Text leads on transparency \u0026 trust. Both do speech-to-text.\n\n- Gladia Speech-to-Text API + MCP: grade B, 69.8/100, rank #225 of 1486. Markdown https://www.anchorterminal.com/tools/gladia-stt.md · JSON https://www.anchorterminal.com/api/v1/tools/gladia-stt.json\n- IBM Watson Speech to Text: grade C, 54.5/100, rank #904 of 1486. Markdown https://www.anchorterminal.com/tools/ibm-watson-stt.md · JSON https://www.anchorterminal.com/api/v1/tools/ibm-watson-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### Gladia Speech-to-Text API + MCP (B)\n\nGood for: Multilingual meetings and calls where live and async transcription in 100+ languages is needed, and for teams who want an MCP server.\n\nAhead on:\n- Reliability, 70 against 40\n- Schema \u0026 documentation, 95 against 55\n- Agent ergonomics, 75 against 66\n- Maintenance \u0026 community, 70 against 33\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: Self-serve audio is used for model training by default unless the account opts out\n\n### IBM Watson Speech to Text (C)\n\nGood for: Enterprises on IBM Cloud needing custom acoustic models, HIPAA on Premium and many locations.\n\nAhead on:\n- Transparency \u0026 trust, 80 against 65\n\nWatch for: No public OpenAPI file or llms.txt\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Gladia Speech-to-Text API + MCP +40\n\n- Gladia Speech-to-Text API + MCP (95): OpenAPI file at api.gladia.io/openapi.json (25). llms.txt (10). Reference pages state purpose per endpoint and the model page says to use `solaria-3` only for async English, French, German, Spanish or Italian (15). Typed bodies with enums and required fields, `audio_url` the only required input for pre-recorded (15). Examples per endpoint and documented error codes (15). Versioned `/v2` paths and a dated changelog (15).\n- IBM Watson Speech to Text (55): No public OpenAPI or other machine-readable definition was found (0). No llms.txt (0). The reference says which parameters each model family supports and the docs cover each feature (15 of 20). Typed parameters with defaults, ranges and enums (13 of 15). curl and SDK examples on every method, and errors with `error`, `code`, `code_description` and `warnings`, with invalid arguments reported as warnings (12 of 15). Versioned `/v1` paths and dated release notes back to 2015 (15). Total 55.\n\n### Maintenance \u0026 community: Gladia Speech-to-Text API + MCP +37\n\n- Gladia Speech-to-Text API + MCP (70): Read as a model, for deprecation notice and model churn rather than release counts, on the lines deepgram-stt was settled on in this run. SDK 2.2.0 on 13 October 2026, three fixes among them limiting list pagination to the configured API, 19 days before 1 November (30). 2.2.1 on 23 October only raises the Python `certifi` floor to distrust a compromised certificate authority and is a version bump with no code changes for JavaScript, so as a dependency-only release it counts half and doesn't set this line, as azure-translator's was read. In the 90 days from 3 August, changelog entries on 8, 9 and 14 September, SDK 2.1.0 (18 and 21 September), 2.2.0 and 2.2.1 (at half), and the MCP server 0.1.0 and 0.1.1 on 24 September (10). The `/v2/transcription` endpoints are marked deprecated in favour of `/v2/pre-recorded` with no removal date, structured data extraction has gone from the OpenAPI file without a changelog entry, and no deprecation policy was found (0 of 10). Public changelog, help centre and Discord (10 of 15). SDK and MCP repository issues couldn't be read, since github.com refuses our reader, so absent (0 of 10). Official JavaScript and Python SDKs current at 2.2.1 (15). The SDK repository has CI, release and OpenAPI type-update workflows, results not seen (5 of 10). 30 + 10 + 0 + 10 + 0 + 15 + 5 = 70.\n- IBM Watson Speech to Text (33): Read as a model. The newest release note is 29 June 2026 (`parameter_set` for large speech models), 130 days ago (10). No dated entries in the 90 days from 8 August (0). Release notes, IBM support and a public docs repository last changed 30 June 2026 (8 of 15). Official SDKs, `ibm-watson` 11.2.0 on PyPI (26 January 2026) and 12.2.0 on npm (January 2026) (10 of 15). CI not read (5 of 10). Total 33.\n\n### Reliability: Gladia Speech-to-Text API + MCP +30\n\n- Gladia Speech-to-Text API + MCP (70): incident.io status page with per-component uptime bars and incident pages, and an RSS feed read on 1 November (20). One major incident in the 90 days from 3 August, a global Pre-Recorded and Real-Time incident on 23 September 2026 from 07:05 to 08:10 caused by a provider network fault, as read on 1 October. The rest are partial and read as minor, a 20-minute full outage and a timeouts incident on 22 September, slower processing on the afternoon of 23 September, and Europe-only degradations on 2, 10, 14 to 15 (elevated errors and timeouts in Europe from 09:07 on 14 September to 13:58 on 15 September), 21, 22 and 28 September and on 3, 4 and 7 October (Pre-Recorded v2 in Europe) (10). Concurrency limits published with numbers, 25 parallel async jobs plus 300 queued and 30 live sessions on paid plans, 3 and 1 on free (15). The docs say a 429 means the concurrency limit, but we found no backoff guidance or Retry-After (5). The pricing page's plan comparison, read on 1 November, lists a 99.9% uptime SLA for Enterprise (10). `solaria-1` and `solaria-3` are GA (10). 20 + 10 + 15 + 5 + 10 + 10 = 70.\n- IBM Watson Speech to Text (40): IBM Cloud has a status page at cloud.ibm.com/status, but it is drawn by script and showed no components or history to our reader, read as gemini-live's script-shell page was (10 of 20, and 5 for no readable history). Plus allows up to 100 concurrent transcription requests across WebSocket and HTTP (15). No 429 or backoff guidance was found in the API reference or the docs repository (0). No SLA was read for the service (0, unchecked). Next-generation and large speech models are GA, language by language (10). 10 + 5 + 15 + 0 + 0 + 10 = 40.\n\n### Transparency \u0026 trust: IBM Watson Speech to Text +15\n\n- Gladia Speech-to-Text API + MCP (65): Closed service with an MIT SDK and MCP server and separate terms for Gladia SAS and Gladia Inc. (15). The statements disagree. The security page gives a 12-month default retention with custom policies for customers and says only Free plan data trains models, while the retention page gives 1 year on free, 3 weeks on paid and zero retention only on Enterprise, and the pricing page says Self-serve is opted in to training by default. ISO 27001 is described as in progress (15). Breaking changes are flagged with dates in the changelog, such as SDK 2.0.0 and the move to credit billing on 3 July 2026 with a 6 to 20 July rollout, but no deprecation policy was found (10). Hosting with a French provider is stated, and no sub-processor list was found (10).\n- IBM Watson Speech to Text (80): Closed service under the IBM Cloud terms (15). The data security page states default logging for improvement with an opt-out, async retention, GDPR deletion by customer ID and plan-level separation, and they agree with each other. The DPA wasn't read (20 of 30). Previous-generation models carried a dated deprecation of 15 March 2022 and removal on 31 July 2023, and release notes say changes are compatible unless noted (18 of 20). Ten locations are named, with sub-processors not read (12 of 20). Total 65.\n\n### Agent ergonomics: Gladia Speech-to-Text API + MCP +9\n\n- Gladia Speech-to-Text API + MCP (75): API reading of the checklist. Add-ons such as summaries, NER and translation are opt-in, so a plain request stays small, but there's no field selection (15). Pre-recorded jobs list with offset, limit and filters (20). Documented error codes, with a 429 for concurrency (15). No idempotency key. The docs warn that a job is already queued once the 200 or `transcription.created` webhook arrives, which is safe-retry guidance of a sort (10). One required parameter and official SDKs in JavaScript and Python (15). The official MCP server adds 8 tools for async jobs, which this API reading doesn't score.\n- IBM Watson Speech to Text (66): API reading of the checklist. Timestamps, word confidence, alternatives and speaker labels are opt-in (15 of 25). Async jobs and custom models list, and async results can go to a callback URL (12 of 20). Structured errors and warnings an agent can act on (15 of 20). Async jobs take a `user_token`, results have a TTL, and jobs can be deleted, with no idempotency key (12 of 20). Most parameters are optional. Official SDKs including Python, Node and Swift, though the Python and Node SDKs last released in January 2026 (12 of 15). Total 66.\n\n## Score by category\n\n| Category | Weight | Gladia Speech-to-Text API + MCP | IBM Watson Speech to Text | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 40 | Gladia Speech-to-Text API + MCP +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 95 | 55 | Gladia Speech-to-Text API + MCP +40 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 66 | Gladia Speech-to-Text API + MCP +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 68 | IBM Watson Speech to Text +3 |\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) | 70 | 33 | Gladia Speech-to-Text API + MCP +37 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 80 | IBM Watson Speech to Text +15 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **69.8 · B** | **54.5 · C** | |\n\n## Facts side by side\n\n| Fact | Gladia Speech-to-Text API + MCP | IBM Watson Speech to Text |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Gladia | IBM |\n| Hosted endpoint | `https://api.gladia.io/v2` | no (local only) |\n| Transports | HTTP, stdio | HTTP, websocket |\n| Auth | API key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | MIT (SDKs and MCP server) | none |\n| Tools exposed | 8 | 0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-23 | 2026-06-29 |\n| Terms last updated | no date given | no date given |\n| Privacy policy last updated | no date given | 2026-08-25 |\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 | not found in the text | 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 | 4 stars, 4.8k npm/wk, 126k PyPI/wk | none |\n| Agent reviews | 3/5 (2) | none |\n\n## How the scores have moved\n\n### Gladia Speech-to-Text API + MCP\n\n- +0.2 on 1 November 2026: terms, correction\n- +0.1 on 27 October 2026: checklist\n- -0.2 on 8 October 2026: checklist\n\n### IBM Watson Speech to Text\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Gladia Speech-to-Text API + MCP.** The `solaria-1` model transcribes live and recorded audio in over 100 languages with code switching, behind an OpenAPI file and SDKs in two languages. Self-serve audio is used for model training unless the account opts out, and Gladia's pages disagree on retention and training defaults.\n\n**IBM Watson Speech to Text.** Watson STT covers sync, async and WebSocket transcription in ten locations, with custom models, $0.02 a minute on Plus and 500 free minutes. There is no machine-readable spec or readable status history, requests are logged for improvement unless opted out, the WebSocket token goes in the URL, and the last release note is from June 2026.\n\n## Before you call either\n\n### Gladia Speech-to-Text API + MCP\n\n1. Don't resubmit a pre-recorded job after a 200 or a `transcription.created` webhook. It's already queued\n2. Pick `solaria-3` only for async EN, FR, DE, ES or IT audio. Anything live or multilingual needs `solaria-1`\n3. A 429 means the concurrency limit, 3 async and 1 live on the free plan. Wait for a running job to finish\n4. Opt the account out of model training in its profile before sending sensitive audio on Self-serve\n5. Split files over 135 minutes or 1,000 MB\n\n### IBM Watson Speech to Text\n\n1. Send `X-Watson-Learning-Opt-Out: true` or opt out at account level before sending sensitive audio\n2. Use the async `/v1/recognitions` interface with a callback for files over 100 MB, up to 1 GB\n3. Pass a large speech or next-generation model name in `model`, since previous-generation models were removed\n4. Tag requests with `X-Watson-Metadata: customer_id=...` so the data can be deleted later\n5. Keep within 100 concurrent requests on Plus across HTTP and WebSocket\n\n## Questions\n\n### Which is better for AI agents, Gladia Speech-to-Text API + MCP or IBM Watson Speech to Text?\n\nGladia Speech-to-Text API + MCP scores 69.8 (B) on agent readiness against IBM Watson Speech to Text's 54.5 (C), and leads in 4 of 7 scored categories. IBM Watson Speech to Text leads on transparency \u0026 trust.\n\n### Do Gladia Speech-to-Text API + MCP and IBM Watson Speech to Text need an API key?\n\nBoth need an API key.\n\n### Can an agent call Gladia Speech-to-Text API + MCP and IBM Watson Speech to Text without installing anything?\n\nGladia Speech-to-Text API + MCP has a hosted endpoint at https://api.gladia.io/v2. No hosted endpoint is listed for IBM Watson Speech to Text.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gladia-stt\", \"b\": \"ibm-watson-stt\"}`. From a terminal: `anchor compare gladia-stt ibm-watson-stt`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gladia-stt.json and https://www.anchorterminal.com/api/v1/tools/ibm-watson-stt.json\n\n## Other comparisons with Gladia Speech-to-Text API + MCP or IBM Watson Speech to Text\n\n- [Amazon Transcribe vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/amazon-transcribe-vs-gladia-stt.md)\n- [Amazon Transcribe vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/amazon-transcribe-vs-ibm-watson-stt.md)\n- [AssemblyAI Speech-to-Text (Universal) vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/assemblyai-stt-vs-gladia-stt.md)\n- [AssemblyAI Speech-to-Text (Universal) vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/assemblyai-stt-vs-ibm-watson-stt.md)\n- [Azure AI Speech speech-to-text vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-gladia-stt.md)\n- [Azure AI Speech speech-to-text vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-ibm-watson-stt.md)\n- [Cartesia Ink vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-gladia-stt.md)\n- [Cartesia Ink vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-ibm-watson-stt.md)\n- [Deepgram Speech-to-Text (Nova-3, Flux) vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/deepgram-stt-vs-gladia-stt.md)\n- [Deepgram Speech-to-Text (Nova-3, Flux) vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/deepgram-stt-vs-ibm-watson-stt.md)\n- [ElevenLabs Scribe Speech to Text API vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-gladia-stt.md)\n- [ElevenLabs Scribe Speech to Text API vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-ibm-watson-stt.md)\n- [Giggy Speech to Text vs Gladia Speech-to-Text API + MCP](https://www.anchorterminal.com/compare/giggy-stt-vs-gladia-stt.md)\n- [Giggy Speech to Text vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/giggy-stt-vs-ibm-watson-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Google Cloud Speech-to-Text](https://www.anchorterminal.com/compare/gladia-stt-vs-google-speech-to-text.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- [Gladia Speech-to-Text API + MCP vs MiniMax Speech-to-Text](https://www.anchorterminal.com/compare/gladia-stt-vs-minimax-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Mistral Voxtral Transcribe](https://www.anchorterminal.com/compare/gladia-stt-vs-mistral-voxtral-transcribe.md)\n- [Gladia Speech-to-Text API + MCP vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/gladia-stt-vs-openai-speech-to-text.md)\n- [Gladia Speech-to-Text API + MCP vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/gladia-stt-vs-rev-ai-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/gladia-stt-vs-smallest-pulse-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/gladia-stt-vs-soniox-stt.md)\n- [Gladia Speech-to-Text API + MCP vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/gladia-stt-vs-speechmatics-stt.md)\n- [Google Cloud Speech-to-Text vs IBM Watson Speech to Text](https://www.anchorterminal.com/compare/google-speech-to-text-vs-ibm-watson-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- [IBM Watson Speech to Text vs Inworld STT](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-inworld-stt.md)\n- [IBM Watson Speech to Text vs MiniMax Speech-to-Text](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-minimax-stt.md)\n- [IBM Watson Speech to Text vs Mistral Voxtral Transcribe](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-mistral-voxtral-transcribe.md)\n- [IBM Watson Speech to Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-openai-speech-to-text.md)\n- [IBM Watson Speech to Text vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-rev-ai-stt.md)\n- [IBM Watson Speech to Text vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-smallest-pulse-stt.md)\n- [IBM Watson Speech to Text vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-soniox-stt.md)\n- [IBM Watson Speech to Text vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/ibm-watson-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": "Gladia Speech-to-Text API + MCP vs IBM Watson Speech to Text", "url": "" } ], "description": "Gladia Speech-to-Text scores 69.8 (B) to IBM Watson Speech to Text's 54.5 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Gladia Speech-to-Text API + MCP B 69.8", "IBM Watson Speech to Text C 54.5", "scores" ], "h1": "Gladia Speech-to-Text API + MCP vs IBM Watson Speech to Text", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/gladia-stt-vs-ibm-watson-stt", "published": "2026-10-01", "section": "tools", "title": "Gladia Speech-to-Text vs IBM Watson Speech to Text (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/gladia-stt-vs-ibm-watson-stt" }, "tokens": { "markdown": 5000, "slim": 2480 }, "version": 1 }