Last refreshed 2026-10-20. Next refresh: weekly.
Why use Voxtral Small Transcribe 3 on Mistral AI Studio?
Mistral AI Studio offers Voxtral Small Transcribe 3 with pay-as-you-go pricing at $0.004/minute. Mistral AI is a French company developing advanced language models and AI technologies.
Compare Voxtral Small Transcribe 3 across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: voxtral-small-transcribe-3-0voxtral-small-transcribe-3-0Request example
voxtral-small-transcribe-3-0.Gotchas
- Use provider model ID "voxtral-small-transcribe-3-0", not the LLMReference slug "voxtral-small-transcribe-3".
Compare Voxtral Small Transcribe 3 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Mistral AI Studio | — | — |
| Vercel AI Gateway | — | — |
Pricing
| Type | Rate |
|---|---|
| Audio minute | $0.004/min |
Capabilities
About Voxtral Small Transcribe 3
Voxtral Small Transcribe 3 is Mistral AI's flagship speech-to-text model in the Voxtral 3 family, released October 20, 2026 as a Public Preview on the Mistral API. It transcribes more than 50 languages, including the 24 official EU languages, with speaker diarization, end-of-turn detection and context biasing, and also supports translation, spoken Q&A, summarization and function calling over audio. Mistral reports state-of-the-art FLEURS and diarization results against Whisper large-v3, Scribe v2, GPT Transcribe and Gemini 3.5 Transcribe. It has a 32k context and costs $0.004 per audio minute; weights are not published.