{"schema":"postcutoff/model@1","as_of":"2026-10-25T23:49:00+01:00","url":"https://postcutoff.com/m/voxtral-small-transcribe-3/","md":"https://postcutoff.com/m/voxtral-small-transcribe-3/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","family":"Voxtral","released":"2026-10-20","status":"preview","type":"audio/speech","modality_in":["audio"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":32000,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_minute":0.004,"unit":"USD per minute of audio (Mistral API)","source":"https://docs.mistral.ai/models/voxtral-small-transcribe-3-0"},"price_line":"$0.004 per minute","access":[{"provider":"Mistral API","model_id":"voxtral-small-transcribe-3-0","endpoint":"https://api.mistral.ai/v1/audio/transcriptions","docs":"https://docs.mistral.ai/models/voxtral-small-transcribe-3-0"},{"provider":"Mistral Studio docs (speech-to-text)","url":"https://docs.mistral.ai/studio/audio/speech-to-text/overview"}],"capabilities":[{"name":"Transcription in 50+ languages incl. all 24 official EU languages","detail":"Mistral's highest-accuracy transcription model; ~4.0-4.1% macro-average WER on FLEURS (45 languages), which Mistral says beats Whisper large-v3, ElevenLabs Scribe v2 and Gemini 3.5 Transcribe (vendor-reported).","first":false,"discovered":"launch","source":"https://mistral.ai/news/voxtral-3"},{"name":"Speaker diarization","detail":"Built-in 'who spoke when'; 18.4% macro-average cpWER on Mistral's diarization chart vs 19.0% for the best competitor shown (pyannote).","first":false,"discovered":"launch","source":"https://mistral.ai/news/voxtral-3"},{"name":"Context biasing without fine-tuning","detail":"Key terms and free-form context text can be passed with the request to improve recognition of names and jargon.","first":false,"discovered":"launch","source":"https://mistral.ai/news/voxtral-3"},{"name":"#3 on Artificial Analysis AA-WER (2.1%)","detail":"Third on the Artificial Analysis non-streaming speech-to-text leaderboard (AA-WER 2.1%, $4.00 per 1,000 min), behind Fun-Realtime-ASR-preview (1.7%) and MAI-Transcribe-2 (2.0%), read 2026-10-25.","first":false,"discovered":"later","source":"https://artificialanalysis.ai/speech-to-text"}],"entry":"2026-10-20-mistral-voxtral-3","notes":"Artificial Analysis speech-to-text (https://artificialanalysis.ai/speech-to-text), read 2026-10-25: rank #3, AA-WER 2.1%, $4.00 per 1,000 minutes. Docs label it v3.0, 'Public Preview' and 'Premier' (API-only; no open weights or Hugging Face release found, license page not read). Model card also says it supports translation, speech Q&A, summarization and function calling; context 32k. Exact language list and maximum audio length not stated on the card. Siblings: voxtral-mini-transcribe-3 (4B, $0.0035/min) and Voxtral Mini Transcribe Realtime 3 (see voxtral-mini-transcribe-3). Successor of Voxtral Transcribe 2 (voxtral-transcribe-2) and the July 2025 Voxtral Small (voxtral-small).","verified":"2026-10-25","body_md":"Mistral's top-accuracy batch transcription model in the Voxtral 3 line (Oct 2026), EU-hosted API.\n\n```bash\ncurl https://api.mistral.ai/v1/audio/transcriptions -H \"Authorization: Bearer $MISTRAL_API_KEY\" \\\n  -F model=voxtral-small-transcribe-3-0 -F file=@audio.mp3\n```\n\nSources: https://mistral.ai/news/voxtral-3 · https://docs.mistral.ai/models/voxtral-small-transcribe-3-0 · https://docs.mistral.ai/models/overview · https://artificialanalysis.ai/speech-to-text","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/","standing":{"kind":"speech and audio","newer_count":0,"newer":[],"before":{"id":"voxtral-tts","name":"Voxtral TTS","org":"Mistral AI","released":"2026-03-23","page_url":"https://postcutoff.com/m/voxtral-tts/"},"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}