---
type: "raw_signal"
id: "voxtral-3-voice-agent-sdk-speech-models-in-4b16e8"
slug: "voxtral-3-voice-agent-sdk-speech-models-in-4b16e8"
title: "Voxtral 3: Voice Agent SDK & Speech Models in 50+ Languages"
description: "Mistral announced Voxtral 3, a family of speech models and a voice-agent SDK."
retrieval_nugget: "Mistral announced Voxtral 3, a family of speech models and a voice-agent SDK."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Mistral announced Voxtral 3, a family of speech models and a voice-agent SDK. The SDK combines listening, reasoning, tool calling, and speaking in a real-time streaming pipeline. The company says Voxtral Small Transcribe 3 supports transcription in 50 languages, with diarization, context biasing, and end-of-turn detection; Voxtral Mini TTS 3 supports 35+ languages and 50+ dialects. Mistral also de"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "mistral.ai"
topics: []
entities: ["Mistral AI","Voxtral 3","Voxtral Small Transcribe 3","Voxtral Mini TTS 3","Voxtral Realtime Transcribe 3"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Mistral has moved from reported voice-mode development to announcing Voxtral 3, a voice-agent SDK and speech-model family for 50+ languages."
prior_refs: ["memory:48d1f64c-ff34-8e5b-a883-99e8db436e5f"]
source_url: "https://mistral.ai/news/voxtral-3"
source_urls: ["https://mistral.ai/news/voxtral-3"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:voxtral-3-voice-agent-sdk-speech-models-in-4b16e8"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/voxtral-3-voice-agent-sdk-speech-models-in-4b16e8/","markdown":"https://newruntime.com/signals/voxtral-3-voice-agent-sdk-speech-models-in-4b16e8.md","json":"https://newruntime.com/signals/voxtral-3-voice-agent-sdk-speech-models-in-4b16e8.json"}
---

# Voxtral 3: Voice Agent SDK & Speech Models in 50+ Languages

## Retrieval answer

Mistral announced Voxtral 3, a family of speech models and a voice-agent SDK.

Mistral announced Voxtral 3, a family of speech models and a voice-agent SDK. The SDK combines listening, reasoning, tool calling, and speaking in a real-time streaming pipeline. The company says Voxtral Small Transcribe 3 supports transcription in 50 languages, with diarization, context biasing, and end-of-turn detection; Voxtral Mini TTS 3 supports 35+ languages and 50+ dialects. Mistral also describes Voxtral Realtime Transcribe 3 as delivering sub-500ms latency in 35+ languages. Voxtral 3 is available through Mistral’s EU-hosted API or for self-deployment. Mistral lists Mini Transcribe 3 at $0.0035 per minute and TTS at $13 per million characters. These performance comparisons and product claims are from Mistral’s announcement.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)