# MiniMax Speech-to-Text (slim)

> MiniMax's speech-to-text API transcribes audio files of up to 500 seconds with its asr-1.0 model in 20 languages, with optional streamed text output, speaker diarisation, segment timestamps and SRT or VTT subtitles.

- Full: https://www.anchorterminal.com/tools/minimax-stt.md (~6,350 tokens) · this version ~1,380 tokens · JSON https://www.anchorterminal.com/tools/minimax-stt.json · canonical https://www.anchorterminal.com/tools/minimax-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/minimax-stt#pricing · reviews https://www.anchorterminal.com/tools/minimax-stt#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**D · 48.4/100 · rank #1114 of 1486 · #19 in Speech-to-text · not agent-ready · confidence medium**


Assessment: MiniMax's ASR API has an OpenAPI file, typed error envelopes and a public price of $0.38 an hour, with diarisation and subtitle output. It takes files of up to 500 seconds only, allows 2 concurrent connections, has no free tier or status component, and no dated release.

## Facts

- Kind: Model API · vendor: MiniMax · category: Speech-to-text · legal entity: Nanonoble Pte. Ltd. · provenance 82/100
- Local only (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Vendor status page: no problems reported, All Systems Operational (2026-11-07 18:21 UTC)
- Surface listed: The speech-to-text endpoint at api.minimax.io/v1/speech_to_text, read from platform.minimax.io docs (guide, API reference, OpenAPI file, rate limits, pricing, release notes) and status.minimax.io history on 6 November 2026, with terms and privacy as read for minimax-voice-cloning on 4 November. No account was made and no request was sent
- Model: `asr-1.0`, the only public model. No release date was found
- Languages: 20, among them Chinese, Cantonese, Japanese, Korean, Thai, Vietnamese, English, French, German, Spanish, Russian, Arabic and Turkish. Without `language` the model detects the dominant language and handles Chinese-English code-switching
- Output: `json` (text, duration, trace ID), `verbose_json` (speaker count and per-segment speaker and timestamps), `srt` or `vtt`. Streaming works with `json` only
- Audio: wav, aiff, flac, alac, mp3, aac, opus or ogg in a container, up to 500 seconds and 50 MB. Raw PCM isn't accepted
- Same company: MiniMax's text models (minimax-api), voice cloning (minimax-voice-cloning), video and speech synthesis (minimax-speech) are listed separately. MiniMax's MCP servers have no transcription tool
- Prices: asr-1.0 $0.0063 per minute of audio

- Scores: Reliability 47, Performance pending, Schema & documentation 82, Agent ergonomics 70, Security & auth 33, Payments & pricing 20, Task success pending, Maintenance & community 6, Transparency & trust 63 · total over the 7 assessed categories
- Why: Reliability, Atlassian Statuspage at status.minimax.io with component history, but its components are LLM, Text-to-Speech and Video Generation, with none… · Schema & documentation, OpenAPI 3.1 for `/v1/speech_to_text`, with eight documented responses (25). · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read as a model. · Transparency & trust, Closed API with clear terms under Singapore law naming Nanonoble Pte.
- Sources: 10, open questions: 4, both in the full twin
- Capabilities: speech.stt, speech.diarisation, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/minimax-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/minimax-stt.svg` or a link to https://www.anchorterminal.com/tools/minimax-stt from a page on minimax.io or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: more in the full twin

## Before you call it

1. Split recordings into pieces under 500 seconds before uploading, since longer audio returns 400
2. Convert to mono 16 kHz or a compressed format to stay under 50 MB
3. Use `verbose_json` for speakers and timestamps, and `json` only when streaming
4. Treat 402 `insufficient_balance_error` as final and ask the user to top up
5. Use `https://api.minimaxi.com` for a mainland China account

## Connect

```bash
curl -X POST https://api.minimax.io/v1/speech_to_text \
  -H "Authorization: Bearer $MINIMAX_API_KEY" \
  -F model=asr-1.0 -F file=@meeting.mp3 -F response_format=verbose_json
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Azure AI Speech speech-to-text | BB | 75.1 | speech.stt, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md |
| OpenAI Speech to Text | BB | 75 | speech.stt, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/openai-speech-to-text.min.md |
| Deepgram Speech-to-Text (Nova-3, Flux) | BB | 74.4 | speech.stt, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/deepgram-stt.min.md |
| Amazon Transcribe | BB | 73.6 | speech.stt, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/amazon-transcribe.min.md |
| ElevenLabs Scribe Speech to Text API | BB | 73 | speech.stt, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)