Cartesia Ink vs MiniMax 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.

MiniMax Speech-to-Text 6

Read as a model. No dated release or change of asr-1.0 was found on the model or API release notes or the status page (0). No dated ASR entries in the last 90 days (0). Support by email and Discord, not tested (6 of 15). No official SDK, and the MCP servers have no transcription tool (0 of 15). No package to judge (0 of 10). Total 6.

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.

MiniMax Speech-to-Text 47

Atlassian Statuspage at status.minimax.io with component history, but its components are LLM, Text-to-Speech and Video Generation, with none for speech to text (10 of 20). With no component, the history holds no record for transcription (5). Limits published with numbers, 2 concurrent connections and 30,000 audio seconds a minute (15). 429 is documented as rate_limit_error, and the general error code page says to retry later, with no backoff figures or Retry-After (7 of 15). No SLA in the terms or docs (0). asr-1.0 is called the current public model with no beta label (10). 10 + 5 + 15 + 7 + 0 + 10 = 47.

Cartesia Ink 35

No x402, MPP or L402 (0). The docs pricing page gives 3 credits a second for ink-2 and the public pricing page gives plan prices and overage rates of $65, $45 and $38 per million credits, all read without a login (20). The Free plan is $0 with 20,000 credits a month, about 1 hour 51 minutes of ink-2 audio. Neither page says whether sign-up asks for a card, and we did not sign up, so 15 of 20. A person creates the key in the Playground in a browser, and the hosted MCP server also needs a browser sign-in (0).

MiniMax Speech-to-Text 20

No x402, MPP or L402 (0). $0.38 an hour published without a login (20). Speech to text is for paid accounts only (0). A person signs up in a browser and funds a balance (0). Total 20.

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.

MiniMax Speech-to-Text 33

Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Plain API keys from the console with no scopes found, and the docs say publicly leaked keys may be disabled, as on minimax-voice-cloning (20 of 30). The terms (effective 30 March 2026), as read for minimax-voice-cloning on 4 November, let MiniMax use input and generated content to operate, maintain, develop and improve its services, with no opt-out found, and the privacy policy rules out only training to profile or target consumers (5 of 20). No retention period for uploaded audio or transcripts was found (3 of 15). Each response carries a trace ID, with no audit log found (5 of 15). No security.txt, disclosure policy, bug bounty or certification found, as on the other MiniMax listings (0 of 20). 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).

MiniMax Speech-to-Text 82

OpenAPI 3.1 for /v1/speech_to_text, with eight documented responses (25). llms.txt and a Markdown copy of every page (10). The guide says when to stream, when to use verbose_json, and that subtitles and diarisation can't be combined with streaming (15 of 20). Typed multipart fields with an enum for response_format, and file limits stated in prose (12 of 15). Python examples and an error table giving HTTP status, error.type and trigger for 400, 401, 402, 413, 422, 429 and 500 (15). Versioned /v1 path, but neither release notes page mentions the ASR API, and the API notes stop at 28 October 2025 (5 of 15). Total 82.

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).

MiniMax Speech-to-Text 63

Closed API with clear terms under Singapore law naming Nanonoble Pte. Ltd., as on the other MiniMax listings (15 of 30). The terms and privacy policy agree that inputs may be used to improve services and that data sits in a United States data centre, with no retention period for audio (8 of 30). No deprecation notice or policy touches the ASR API (10 of 20, for the dated notices elsewhere on the API release notes). Data location stated as the United States and an EU representative named, with third parties only by category (10 of 20). Total 43.