Voxtral TTS 3
Voxtral TTS 3 is Mistral's text-to-speech model, released October 20, 2026 in public preview. The model card lists voxtral-mini-tts-3-0, voxtral-mini-tts-3, voxtral-mini-tts-latest, and the realtime aliases voxtral-mini-tts-realtime-3-0, voxtral-mini-tts-realtime-3, and voxtral-mini-tts-realtime-latest.
Provider
Mistral AI
Model family
Mistral AI
Text to speech
Cost tier
Voxtral Mini Tts
Status
Current
Release Oct 20, 2026
Why teams choose it
Complex reasoning
Useful for workflows that require structured thinking, multi-step logic, and deeper analysis than lightweight models provide.
Long-context analysis
Helps teams summarize, compare, and extract insights from long documents without losing important nuance.
Mistral AI roadmap vigilance
Use published model pages—not stale marketing blurbs—for modalities, quotas, pricing, and policy; schedule revalidation tied to vendor release notes.
Cost-efficient routing
Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.
Tradeoffs to know
- Public preview.
- The pricing page lists one character rate for this model card, including the realtime aliases.
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Technical specs
- Inputs
- text, audio
- Outputs
- audio
- License
- Proprietary API
- Status
- public preview
- Realtime Api Id
- voxtral-mini-tts-realtime-3-0
- Input Usd Per Million Characters
- 13
- Capabilities
- Zero-shot and professional voice cloning
- Streaming TTS
- 35+ languages and 50+ dialects
Mistral AI family lineup
Current models
Related models
Voxtral TTS 3 FAQ
What is Voxtral TTS 3?
Voxtral TTS 3 is Mistral's text-to-speech model, released October 20, 2026 in public preview. The model card lists voxtral-mini-tts-3-0, voxtral-mini-tts-3, voxtral-mini-tts-latest, and the realtime aliases voxtral-mini-tts-realtime-3-0, voxtral-mini-tts-realtime-3, and voxtral-mini-tts-realtime-latest. It takes text and audio and returns audio, with zero-shot and professional voice cloning, 35 or more languages, 50 or more dialects, streaming with about 90 ms to first audio, 5 output formats, 34 emotion tags, and 2 pace tags. The published price is $13 per million characters.
When does Voxtral TTS 3 fit best?
Multilingual speech generation
What should teams watch out for with Voxtral TTS 3?
The pricing page lists one character rate for this model card, including the realtime aliases.
Explore next
Models, tools, and comparisons that connect to this reference.