Google Cloud Speech-to-Text vs MiniMax Speech-to-Text

Google Cloud Speech-to-Text 85

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. OAuth 2.0 with service accounts and IAM roles, scoped per project, no API key in the documented V2 flow. The token can also travel in the URL. Google's OAuth guide accepts it as an access_token query parameter, the V2 discovery document (revision 20261001) lists access_token, oauth_token and key as query parameters, and on 1 November speech.googleapis.com/v2/projects/example-project/locations/global/recognizers answered 401 "missing required authentication credential" with no token and 401 "invalid authentication credentials" with a made-up ?access_token=, so the token is read from the query string. That takes the 10-point deduction, as every Google API listing does in this run (Gmail, Sheets, Drive and Calendar on 17 October, Ads, Model Armor, Secret Manager and Document AI on 1 November) (20). Audio isn't used for training unless the project opts in to data logging (20). Streaming and sync audio is processed in memory and not stored, and batch results are kept for a short window (15). Cloud Audit Logs cover Google Cloud APIs, though we didn't confirm which Speech methods they record (10). Valid security.txt, Google's vulnerability reward programme, SOC 2 and ISO 27001, and public Cloud security bulletins (20). 20 + 20 + 15 + 10 + 20 = 85.

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.

Google Cloud Speech-to-Text 75

Google Cloud status page with a per-product history (20). One incident lists Speech-to-Text in the 90 days from 3 August, the europe-west2 incident of 20 October, 06:00 to 12:08 UTC, which named 38 products in that one region. A single-region incident is partial and read as minor, as this run reads partial incidents. The other three Google Cloud incidents since 3 August (20 August, 1 September, 8 and 9 October) don't list Speech-to-Text. The public page only shows broad incidents. Minor only (20). Quotas published with numbers, 300 concurrent streams, 300 sync and 150 batch requests a minute per region, streams up to 5 minutes and sync up to 1 minute (15). The Speech quotas page (last updated 26 October 2026) still says nothing about the error a quota breach returns or how to back off, and we don't count Google's general API design guide for this API (0). Speech-to-Text SLA of 99.9 per cent monthly uptime with credits of 10 to 50 per cent, per the 1 October check, not re-read on 1 November (10). Chirp 3 GA since 2025-10-13 in us and eu, though 82 of its 111 locales were preview on 1 October (10). 20 + 20 + 15 + 0 + 10 + 10 = 75.

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.

Google Cloud Speech-to-Text 87

Closed service under the Google Cloud terms (15). The data logging page, the terms and the privacy notice agree that audio isn't used for training without opt-in, and a data processing addendum and sub-processor list exist (25). Google Cloud's terms carry a notice period before a GA capability is discontinued, but we found no dated Speech-to-Text deprecation notices (15). us and eu multi-region endpoints and a public sub-processor list (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.

Google Cloud Speech-to-Text 25

The newest release note is still 2025-11-13, Chirp 3 preview in four more regions (page last updated 26 October 2026), 353 days ago (0). In the 90 days from 3 August we counted no release note and one Python client release, google-cloud-speech 2.41.0 on 1 October, whose only change is declaring Python 3.15 support. A release that doesn't change the service counts half on the 90-day line and can't set the recency line, so neither line moves (0). The last client release that touched the API was 2.37.0 on 26 February 2026 (endpointing sensitivity for streaming). Release notes, a public issue tracker and paid support (10). Official client libraries in seven or more languages (10). Package CI not checked (5). 0 + 0 + 10 + 10 + 5 = 25.

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.