Mistral AI
Mistral: Voxtral Mini TTS
mistralai/voxtral-mini-tts-2603
Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.
Input
$16
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
4.1K
tokens
Speech output · Token reference fields do not establish an output-unit price.
Limits
Context
4,096
tokens
Max output
3,276
80% of the context window
Model facts
Author
Mistral AI
Tokenizer
Mistral
Modality
Text -> Speech
Created
Apr 19, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextOutput · Speech