---
id: "2026-03-23-mistral-voxtral-tts"
url: "https://postcutoff.com/e/2026-03-23-mistral-voxtral-tts/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-03-23"
date_precision: day
category: open-source
importance: 3
confidence: high
status: [Confirmed]
sources: 5
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-03-23-mistral-voxtral-tts/

# Mistral releases Voxtral TTS, an open-weight 4B text-to-speech model with 3-second voice cloning

On 2026-03-23 Mistral launched Voxtral TTS, its first text-to-speech model: a 4B-parameter model with open weights (CC BY-NC 4.0) that clones a voice from ~3 seconds of audio in 9 languages and, per Mistral, beats ElevenLabs Flash v2.5 in 68.4% of human preference tests, priced at $0.016 per 1K characters via API.

## Key facts
- API id voxtral-tts-2603; HF weights mistralai/Voxtral-4B-TTS-2603 (CC BY-NC 4.0, non-commercial)
- Architecture: 3.4B transformer decoder + 390M flow-matching acoustic transformer + 300M neural codec
- 9 languages: English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, Arabic
- ~70 ms model latency, ~9.7x real-time factor, up to 2 minutes of native audio
- 68.4% win rate vs ElevenLabs Flash v2.5 in multilingual voice-cloning preference tests (Mistral)
- Price: $0.016 per 1K characters
- Followed Voxtral Transcribe 2 (2026-02-04): Voxtral Mini Transcribe V2 ($0.003/min) and open Apache-2.0 Voxtral Realtime 4B

## What happened

Mistral added speech output to its Voxtral audio family. Voxtral TTS is served on the Mistral API
(`/v1/audio/speech`), in Le Chat and Mistral Studio, and its weights were published on Hugging Face under a
non-commercial license. Six weeks earlier Mistral had shipped Voxtral Transcribe 2, including the open Apache-2.0
Voxtral Realtime streaming ASR model (sub-200 ms latency).

## Why it matters

With both open ASR and open TTS, Mistral became one of the few frontier labs offering a full open-weight voice stack,
giving European and self-hosting customers an alternative to ElevenLabs and OpenAI voices. Quality comparisons are
Mistral-reported.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Mistral AI - Speaking of Voxtral](https://mistral.ai/news/voxtral-tts) (mistral.ai, official)
2. [Mistral docs - Voxtral TTS model card](https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03) (docs.mistral.ai, docs)
3. [Hugging Face - Voxtral-4B-TTS-2603](https://huggingface.co/mistralai/Voxtral-4B-TTS-2603) (huggingface.co, code)
4. [Mistral AI - Voxtral Transcribe 2](https://mistral.ai/news/voxtral-transcribe-2) (mistral.ai, official)
5. [SiliconANGLE - Mistral releases an open-weights 'speaking' AI model](https://siliconangle.com/2026/03/26/mistral-releases-open-weights-speaking-ai-model-voxtral-tts/) (siliconangle.com, press)

## Changes

- 2026-09-29 (filed): Created

## Related

- Models: [Voxtral TTS](https://postcutoff.com/m/voxtral-tts/) (`voxtral-tts`), [Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)](https://postcutoff.com/m/voxtral-transcribe-2/) (`voxtral-transcribe-2`)