Cartesia Ink vs IBM Watson Speech to Text

Cartesia Ink 84

Read as a model, on the lines deepgram-stt, gladia-stt and cartesia-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The cartesia-mcp server, which has a speech_to_text tool, released 0.28.1 on 30 October 2026 with a bug fix, after 0.27.0 (20 October) and 0.28.0 (27 October). The model page still dates ink-2 and ink-preview 17 September 2026 (30). In the 90 days from 3 August the SDKs released 4.0.0, 4.0.1, 4.1.0 and 4.2.0 (14 August to 2 September) and the MCP server several releases, with changelog entries for August and September (10). The deprecations page gives dated sunsets, and Sonic-2, Sonic Turbo and sonic-3-2025-10-27 were sunset after 20 October 2026, announced in the July changelog. No minimum notice period is stated and no Ink model has been retired, read as cartesia-tts is on the same page (5 of 10). The changelog has speech-to-text entries in May, June, July and September 2026, dated by month only, and no October entry (11 of 15). The Python SDK repository had 4 open issues on 9 October, per that check, not re-read on 1 November since GitHub's pages answered 403 (5 of 10). Official cartesia and @cartesia/cartesia-js SDKs at 4.2.0 (2 September 2026), generated for API version 2026-08-14 (15). CI workflows, release automation and lock files in both SDK repositories, with dependency updates merged on 23 October (8 of 10). 30 + 10 + 5 + 11 + 5 + 15 + 8 = 84.

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.

Cartesia Ink 89

Model reading. The docs index links an OpenAPI file (latest.yml) and AsyncAPI files for the WebSocket endpoints, and each reference page embeds its part of them (25). llms.txt with a Markdown twin of every page (10). The comparison page says which of the three endpoints to use and when, and the turn detection guide explains each event and threshold (18 of 20). The AsyncAPI definition has enums for encoding and cartesia_version, minimum and maximum values on the four turn settings and required fields marked. model is a plain string on the auto endpoint (13 of 15). Example scripts for each endpoint in Python and TypeScript and an errors page with nine codes. model_sunsetted appears on the deprecations page and not in that table, and the docs say a wrong encoding or sample_rate might not return an error (11 of 15). Dated API versions through the Cartesia-Version header and a changelog grouped by month with no day dates (12 of 15).

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.

Cartesia Ink 73

Hosted reading. The status page at status.cartesia.ai (incident.io) lists Speech to Text as its own component in four regions (20). Its RSS feed, re-read on 1 November, now names each incident's components. In the 90 days from 3 August two incidents touch speech-to-text, both partial and read as minor, as this run reads one region or some requests. On 2 September some clients in the US regions saw connection errors that cleared on retry (Text to Speech and Speech to Text, US), and on 7 October customers in the US regions saw higher latency for some API requests, from 12:29 to about 18:23 (partial outage, Text to Speech, Speech to Text and Voice Cloning, US). The 3 September throttling named only Text to Speech in APAC, the 8 October errors only the Playground and Voice Agents, and the 15 October Playground outage says API services were unaffected. The 1 August API-wide incident has left the window. Minor only (20). Concurrency limits are published per plan, 8, 12, 20 and 60 concurrent STT requests, with a 3-minute idle timeout on sockets (15). Exceeding the limit returns 429 with the concurrency_limited code, and the SDKs retry 429 and 5xx twice with backoff on HTTP calls. No Retry-After header, backoff guidance or reconnection advice for a dropped socket was found (8 of 15). No SLA was found for any plan (0). ink-2 is marked Stable on the model page re-read on 1 November, with ink-preview as the preview line (10). 20 + 20 + 15 + 8 + 0 + 10 = 73.

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.

Cartesia Ink 47

Model reading. Standard keys (sk_car_...) and admin keys are separate types that are not interchangeable, and a server can mint an access token with an stt grant that lasts at most one hour. That token travels in the access_token query parameter on WebSockets, the API key itself goes in a header, and no key limited to speech-to-text was found. The STT WebSocket definition, re-read on 1 November, lists access_token in the query as a security scheme. The checklist takes 10 off for a secret that can travel in a URL query string as a documented option, and this run takes the full 10 for short-lived OAuth tokens in ?access_token= on every Google API listing, so the earlier 5 is brought into line (26, less 10, 16 of 30). The terms, last revised 14 June 2024, say inputs, outputs and interactions may be used to train models unless otherwise agreed, with an opt-out form in the Playground's data controls (5 of 20). Zero data retention covers STT audio and transcripts and is limited to the Enterprise plan. No retention period for other plans was found, and the DPA gives 180 days for deletion after termination (5 of 15). Credit usage and key metadata are readable through admin endpoints. No audit log was found (7 of 15). security.txt is valid until 3 October 2027 with a contact and a policy link to the trust centre. The docs and pricing page state SOC 2 Type II, HIPAA and PCI-DSS. The trust centre is drawn by script and was not read, and no bug bounty was found (14 of 20). 16 + 5 + 5 + 7 + 14 = 47.

IBM Watson Speech to Text 68

Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. IAM API keys per instance with Reader, Writer and Manager roles and short-lived bearer tokens (30). The WebSocket interface takes the token as an access_token query parameter, so 10 off (20 of 30). Request and response data are logged by default to improve the service, and any account can opt out per account or per request (10 of 20). Async results expire after a week by default (results_ttl shortens it), a delete method exists, and DELETE /v1/user_data removes data by customer ID (10 of 15). Activity Tracker events record changes to the service's state (10 of 15). Valid security.txt to 6 December 2026, PSIRT and HackerOne, HIPAA readiness on Premium. Certifications weren't read (18 of 20). Total 68.

Cartesia Ink 68

The service is closed and the SDKs are Apache-2.0. The Terms of Service cover the website, its subdomains and APIs, were last revised on 14 June 2024, describe a platform for synthesised sound and never mention transcription (12 of 30). The terms and privacy policy agree that content may be used for training with an opt-out. The DPA says Cartesia will not retain or use customer personal data beyond performing the services, which sits uneasily with the training licence. No retention period is given outside zero data retention, and the privacy policy says the services are designed for users in the United States only while regional endpoints are sold in four other regions (12 of 30). A deprecations page with dated sunsets and a stated promise to preserve fields for a pinned Cartesia-Version (15 of 20). The DPA promises 30 days' notice of sub-processor changes to subscribers and points to a list in the trust centre, which we could not read. Regional deployments are named for Enterprise only (10 of 20).

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.

Cartesia Ink 74

API reading, as for the other speech-to-text listings. Turn events carry a cumulative transcript that is never revised, so an agent reads one turn.end a turn, and word timestamps are opt-in on the manual and batch endpoints (20 of 25). There is nothing to page through. Batch takes a file of any length without client chunking, keyterms steer vocabulary, and there is no diarisation or subtitle output (12 of 20). Errors are structured JSON with error_code, title, message, request_id and an optional doc_url on API version 2026-03-01 and later (17 of 20). Transcription holds no state to duplicate and the SDKs retry failed HTTP calls. A realtime session cannot be resumed, and nothing on reconnecting was found (12 of 20). Realtime needs model, encoding, sample_rate and the version, turn settings have documented defaults, and there are official Python and TypeScript SDKs. Realtime accepts raw PCM only (13 of 15).

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.