Mistral AI · Speech (transcription or voice)
Voxtral TTS
Text-to-speech with zero-shot voice cloning (no transcript needed for the voice prompt), 9 languages and ~90ms time-to-first-audio. Billed per character, not per token: input is free, output is $16 per million characters ($0.016 per 1,000 characters). Weights are CC BY-NC 4.0, so commercial self-hosting is not permitted — use the API. Alias: voxtral-mini-tts-latest.
Open weights · Non-commercial (CC-BY-NC) · Data checked September 6, 2026 · Not a hands-on evaluation
Model ID voxtral-mini-tts-2603
- Parameters
- 4B dense
- Architecture
- Dense
- Context window
- Not recordedMaximum input
- Max output
- Not recordedPer response
- Input price
- $0.00 per 1M tokens
- Output price
- Not published
- Cached input
- $0.00 per 1M tokens
- Blended price
- Not available3:1 input to output
- Knowledge cutoff
- Not recorded
- Released
- 2026-03-23
- Status
- ga
- Size band
- Up to 4B
License and openness
Voxtral TTS is released under the CC-BY-NC-4.0. This license does not permit commercial use without a separate agreement with the provider. It is suited to research, evaluation and personal projects. License terms can change between versions; confirm the text published with the weights you download.
Capabilities
| Input modalities | text |
|---|---|
| Output modalities | audio |
What it is for
Billed per character, not per token: input is free, output is $16 per million characters ($0.016 per 1,000 characters). Weights are CC BY-NC 4.0, so commercial self-hosting is not permitted — use the API. Alias: voxtral-mini-tts-latest.
Cost at list price
| Input | $0.00 per 1M tokens |
|---|---|
| Output | Not published |
| Cached input | $0.00 per 1M tokens |
| Blended, 3:1 | Not available |
The provider publishes no per-token price for this model. Any price you see elsewhere belongs to a third-party host, and running the weights yourself has hardware costs instead.
A recorded $0.00 is preserved from the reference as recorded. It does not promise free access; check the provider’s current terms.
Estimate a workload across all models ↗Sources
- Source: docs.mistral.ai ↗
- Mistral AI pricing ↗
- API docs ↗
- Full reference record for Voxtral TTS ↗
- Mistral AI in the reference ↗
Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.
Other open-weight models from Mistral AI
- Mistral Medium 3.5 · 128B dense
- Mistral Large 3 · 675B total · 41B active
- Mistral Small 4 · 119B total · 6.5B active
- Ministral 3 14B · 14B dense
- Ministral 3 8B · 8B dense
- Ministral 3 3B · 3B dense
- Z.ai GLM 5.2 · Not recorded
- Leanstral 1.5 · 119B total · 6.5B active
- Voxtral Small · 24B dense
- Voxtral Mini Transcribe Realtime · 4B dense
- Shieldstral 1.0 · 3.8B dense