Mistral: Voxtral Small Transcribe 3
- by mistralai
- mistralai/voxtral-small-transcribe-3-0
Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited...
What the numbers mean
- Context window65,536 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 49,000 words, or 98 pages.
- Max output52,428 tokens
- The longest single reply it can write: about 39,000 words.
- Input price$66.67 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs about $0.09.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiesaudio in, transcription out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.