Mistral AI · voice model

Voxtral TTS

Voxtral TTS is a Mistral AI voice model released Mar 23, 2026; Mistral AI's newest voice model in our dataset is Voxtral 3. Mistral's text-to-speech model with zero-shot voice cloning and streaming, released Mar 23, 2026. Verified against vendor sources on Oct 26, 2026.

Reported Last verified Oct 26, 2026 · All models · JSON · Markdown

ReleasedMar 23, 2026

Innot verifiedOutAudio

Key facts

Voxtral TTS: key facts with sources
Fact	Value	Source
Vendor	Mistral AI	n/a
Released	Mar 23, 2026	source
Status	generally available	n/a
API id	voxtral-mini-tts-2603	source
Output	audio	source
Pricing	Speech output $16 (per 1M characters)	source

Where Voxtral TTS sits in our data

Released Mar 23, 2026 (week 13 of 2026), in March 2026. Other models in our data released that month: Gemma 4, Cohere Transcribe, GPT-5.4 mini, Mistral Small 4, Grok 4.20, GPT-5.4.
The previous Mistral AI model we track is Mistral Small 4 (Mar 16, 2026), 7 days earlier.
Mistral AI tools we cover: Mistral Le Chat.
All releases by date: AI model releases by month · new AI models this week.

How Voxtral TTS differs from Voxtral 3

Read from the recorded facts of the two models, not from a head-to-head test. We have not run either.

Status is generally available, against public preview.
Voxtral TTS came out 211 days before Voxtral 3.
Facts for the other model: Voxtral 3.

What we tested

Nothing yet. We have not run Voxtral TTS ourselves, so every fact on this page is Reported from the sources below. When we do test it, the scope will be stated here and in our test logs. See methodology.

Not verified, left out

We could not confirm these on a vendor page, so we do not state them.

License and weights status were not captured.