# Voxtral TTS

Our state-of-the-art text-to-speech model with zero-shot voice cloning. Supports 9 languages, streaming with ~90ms time-to-first-audio, and no transcript required for voice prompts.

- API names: `voxtral-mini-tts-2603`, `voxtral-mini-tts-latest`
- Status: Deprecated
- Type: Open, Specialist
- Release date: 2026-03-23
- Version: 26.03
- Input: text, audio
- Output: audio
- Features: tts, voice-cloning
- Speed rating: 4.5/5
- Performance rating: 4/5
- Pricing: Input $16 /M Chars
- Licenses: CC BY-NC 4.0
- Open weights: [Weights](https://huggingface.co/mistralai/Voxtral-4B-TTS-2603), 4B parameters, CC BY-NC 4.0
- Deprecation date: 2026-10-31
- Retirement date: 2027-04-30
- Replacement: [Voxtral TTS 3](/models/voxtral-mini-tts-3-0)