Gladia Speech-to-Text API + MCP vs MiniMax Speech-to-Text

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.

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.

Gladia Speech-to-Text API + MCP 65

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Plain revocable API keys in the x-gladia-key header. Live sessions connect to a WebSocket URL minted per session by POST /v2/live, which we don't deduct for (20). The pricing page, read on 1 November, says Self-serve, the paid pay-as-you-go plan, is opted in to model training by default with a free opt-out in the profile, and Enterprise is opted out by default. The security page still says only Free plan data is used for training. We score the pricing page's default, as for AWS's default use with an opt-out (10 of 20). Retention is documented and jobs can be deleted, but zero retention needs Enterprise per the retention page (10). Job history through the list endpoint and dashboard, no audit log of key actions found (10). SOC 2 Type 1 and Type 2, a bug bounty programme that doubles as the disclosure route, no security.txt (404 on 1 November) and no public advisories found. The SDKs fixed an API key leak on cross-origin redirects in 2.1.0 (September) and limited list pagination to the configured API in 2.2.0 (13 October), both released. ISO 27001 is in progress, not held (15). 20 + 10 + 10 + 10 + 15 = 65.

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.

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.

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.

Gladia Speech-to-Text API + MCP 40

No x402, MPP or L402 (0). Per-hour prices in euros published without a login, re-read on 1 November, async from 0.27€ an hour on solaria-1 and 0.16€ on solaria-3, real-time 0.68€, add-ons per hour (20). A one-time €50 credit, with no card per the 1 October check (20). A person signs up in a browser (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.

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).

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.

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.

MiniMax Speech-to-Text 70

API reading of the checklist. The default json returns only text, duration and a trace ID, with segments and subtitles opt-in (22 of 25). No lists to page. response_format and language are the output controls (12 of 20). Typed error envelopes with the real HTTP status, an error type and request_id, and 402 for an empty balance (18 of 20). Calls are synchronous with no idempotency key (10 of 20). Two fields, a model and a file. No official SDK, and MiniMax's MCP servers don't cover transcription (8 of 15). Total 70.