Post-Cutoff
Search For AI agents

Mistral AIVoxtral familyPreviewSpeech and audioReleased 20 Oct 2026

Voxtral TTS 3 (Voxtral Mini TTS 3)

Mistral’s Voxtral 3 text-to-speech model for voice agents and narration.

Model idvoxtral-mini-tts-3-0

Price$13 per 1M characters

Checked25 October 2026

Where it stands

No newer speech and audio model in our registry yet.

All speech and audio models

Before it from Mistral AI
Voxtral TTS23 Mar 2026
Weights
Closed weights; access is hosted only.

How to call it

2 ways to use Voxtral TTS 3 (Voxtral Mini TTS 3), with the model id each provider expects.

Providers, model ids, endpoints and docs for Voxtral TTS 3 (Voxtral Mini TTS 3)
ProviderModel idEndpointDocs
Mistral API voxtral-mini-tts-3-0 https://api.mistral.ai/v1/audio/speech docs.mistral.ai
Mistral Studio docs (text-to-speech) docs.mistral.ai

Pricing

Prices for Voxtral TTS 3 (Voxtral Mini TTS 3)
Per 1M characters$13

As published: “USD per 1M characters (Mistral API)”.

Source: docs.mistral.ai, checked 25 October 2026.

Specs

Input
Text and audio
Output
Audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
20 October 2026
Status
Preview
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Context-following emotion with explicit controls

    Adapts emotion, pacing and emphasis to the conversation; explicit `emotion`, `pacing` and `emphasis` instruction variables; the model card lists 34 emotion tags and 2 pace tags.

    Source: mistral.ai

  • Pro Voice adaptation

    Professional voice cloning reproduces a speaker’s character, emotional range and style across languages from about 30 minutes of audio; zero-shot cloning also listed on the card.

    Source: mistral.ai

  • Streaming with ~90 ms time to first audio

    Batch and realtime synthesis on /v1/audio/speech, roughly 90 ms time-to-first-audio and five output formats (model card).

    Source: docs.mistral.ai

Notes

Artificial Analysis TTS arena (https://artificialanalysis.ai/text-to-speech/leaderboard), read 2026-10-25: rank #12, Elo 1219, $13.0 per 1M characters. Docs: v3.0, ‘Public Preview’, ‘Premier’ (API-only; no open weights found, unlike the CC BY-NC Voxtral TTS of March 2026). Language count conflicts: the launch post says 35+ languages and 50+ dialects (voice presets in 18 languages), while the model card says nine supported languages; unresolved. Parameter count not stated. Voice-agent SDK (LiveKit-based, SIP/WebRTC) launched alongside at $0.04/min (Mistral Small 4) or $0.08/min (larger model). Successor of voxtral-tts (voxtral-tts-2603).

Call POST https://api.mistral.ai/v1/audio/speech with model: voxtral-mini-tts-3-0 (request schema and voices: https://docs.mistral.ai/studio/audio/text-to-speech/overview).

Sources: https://mistral.ai/news/voxtral-3 · https://docs.mistral.ai/models/voxtral-mini-tts-3-0 · https://docs.mistral.ai/models/overview · https://artificialanalysis.ai/text-to-speech/leaderboard