模型发布IMAGE

Mistral Voxtral 3: speech model family with ASR, TTS and voice agent SDK

Voxtral 3 bundles Mini/Small ASR with real-time streaming, multilingual TTS, and a low-latency voice agent SDK with tool calling, via API or self-hosted.

Guillaume Lample @ NeurIPS 2024

@GuillaumeLampleArchived 9 days agoOriginally posted 2026.10.21

Mistral Voxtral 3: speech model family with ASR, TTS and voice agent SDK (image 1 of 2)

Mistral Voxtral 3: speech model family with ASR, TTS and voice agent SDK (image 2 of 2)

Guillaume Lample @ NeurIPS 2024 @GuillaumeLampleOriginally posted 2026.10.21

Open original on X

🎙️ Introducing Voxtral 3 ! A new family of SOTA speech models: ASR: Mini & Small for batch transcription, plus real-time streaming TTS: expressive, multilingual speech, batch + streaming Voice agent SDK: low-latency conversations + tool calling Available via API or on your own infrastructure !

This post quotes another post: “Mistral Voxtral 3: speech models powering a new voice agents API”

x.com/guillaumelample/status/2112591060052656585Archived 2026.10.21 10:22