# Voxtral TTS

id: ent_voxtral-tts  
kind: product  
timeline: /timelines/voxtral-tts.md  
page: /record/voxtral-tts  

Open-weights text-to-speech model for voice agents, made by Mistral AI. Proposed by the feed ingest from Mistral AI; not yet reviewed.

## All claims

One claim per line, newest first. Superseded claims stay visible.

- [Voxtral TTS](/record/voxtral-tts.md) | developer | [Mistral AI](/record/mistral-ai.md) | valid 2026-03-23 to present | conf 0.70 | unverified | [clm_9328DCC29F1A](/claim/clm_9328DCC29F1A.md)
  sources: https://mistral.ai/news/voxtral-tts/
- [Voxtral TTS](/record/voxtral-tts.md) | released | Voxtral TTS | valid 2026-03-23 to present | conf 0.50 | unverified | [clm_9909076EBEDE](/claim/clm_9909076EBEDE.md)
  sources: https://mistral.ai/news/voxtral-tts/
---

AsOf is a temporal fact ledger: a structured, dated, sourced record of what is true and what changed, built for AI retrieval.