voxtral-mini-tts-3-0

Name: voxtral-mini-tts-3-0
Author: Mistral AI

ttsapache-2.0

Our state-of-the-art text-to-speech model with zero-shot voice cloning and professional voice cloning. Supports 35+ languages and 50+ dialects, streaming with ~90 ms time-to-first-audio, 5 output formats, 34 emotion tags, and 2 pace tags.

Capabilities

Show unsupported (11)

Infrastructure

Streaming

Fine-tuning

Details

ProviderMistral AI

Creatormistral

Familyvoxtral

Licenseapache-2.0

Statusactive

Typetts

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters—

Architecture—

Max chars—

Sample rate—

Voices—

Languages—

Release date—

Sourceofficial

Family Comparison: voxtral

Model	Caps	Max duration	Sample rate	Channels	Languages	Genres
voxtral-mini-transcribe-3-0	SF	—	—	—	—	—
voxtral-mini-transcribe-realtime-3-0	SF	—	—	—	—	—
voxtral-mini-transcribe-realtime	TSF	—	—	—	—	—
voxtral-mini-tts-3-0	SF	—	—	—	—	—
voxtral-mini-tts	TSF	—	—	—	—	—
voxtral-mini	TSF	—	—	—	—	—
voxtral-small-transcribe-3-0	TSF	—	—	—	—	—
voxtral-small	TSF	—	—	—	—	—
voxtral-tts	TSF	—	—	—	—	—

API

GET/v1/models/mistral/voxtral-mini-tts-3-0