LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · Mistral AIMaterial2 min de leituraEditorial DisconfirmAI

French AI Firm Mistral Releases Voxtral 3: Integrating Transcription, TTS, and Voice Agent SDK

Mistral launches the Voxtral 3 speech model family and SDK, supporting 50+ language transcription and emotion-adaptive TTS, with the Small model ranking third on independent benchmarks.

2026-10-22 15:00 GMT+8

French artificial intelligence company Mistral AI officially released Voxtral 3 on October 20, 2026. This product family includes three speech-to-text (ASR) models, one text-to-speech (TTS) model, and a voice agent SDK built on LiveKit. The release aims to address challenges in end-to-end voice agents regarding real-time performance, multilingual support, and complex workflow handling.

Voxtral Small Transcribe 3 is the flagship batch transcription model, supporting 50 languages (including 24 official EU languages) with speaker diarization and context biasing capabilities. According to data from independent evaluation firm Artificial Analysis, its weighted average word error rate (AA-WER) is 2.1%, ranking third on the platform behind Fun-Realtime-ASR-preview and Microsoft's MAI-Transcribe-2. Mistral's self-reported data shows a forced-language WER of 4.1% on the FLEURS 45 benchmark, outperforming Whisper large-v3 (16.0%).

Beyond transcription, Voxtral Mini TTS 3 introduces natural speech synthesis technology capable of adjusting emotion, pace, and emphasis based on conversational context, supporting over 35 languages and 50+ dialects. The accompanying Voice Agent SDK integrates real-time transcription, large language model reasoning (such as Mistral Small 4), and speech generation into a single streaming pipeline. Each turn completes in under one second, with support for phone systems via SIP and browser/app sessions via WebRTC.

All models are currently in public preview and accessible via the Mistral API. Pricing for Voxtral Mini Transcribe 3 batch transcription is $0.0035 per minute, Small version is $0.004 per minute, realtime transcription is $0.008 per minute, and TTS services cost $13 per million characters. Notably, while batch transcription performs strongly, Voxtral Mini Transcribe Realtime 3 has a word error rate of 7.4% at low latency (240 ms), higher than Gemini 3.5 Realtime's 4.2%, indicating an accuracy trade-off in extreme low-latency scenarios.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

Fontes

  • mistral.ai↗
  • marktechpost.com↗
Tópico

Mistral AI

法国人工智能公司 Mistral AI 于2026年10月21日正式发布 Voxtral 3 语音模型家族及配套开发者套件(SDK)。该系列旨在解决实时语音智能体在“听、想、说、做”四个环节难以协同的痛点,支持超过50种语言的转录和35种以…

3 etapas5 peçasAtualizado 2026-10-22 11:57

Como chegamos aqui

  1. 2026-10-21Mistral AI 官方宣布推出 Voxtral 3 语音模型家族,包括三个转录模型和一个文本转语音模型,以及用于构建实时语音智能体的 SDK。mistral.ai ↗
  2. 2026-10-21第三方评测显示,Voxtral Small Transcribe 3 在 Artificial Analysis 排名中获 AA-WER 2.1%,位列行业第三,仅次于 Fun-Realtime-ASR-preview 和 Microsoft MAI-Transcribe-2。marktechpost.com ↗
  3. 2026-10-21Mistral 同步发布了另一款大模型 Mistral Large 4(代号 Le Chonk),宣称拥有1万亿参数,在网络安全和金融领域处于开源模型领先地位,目前开放公开预览。youtube.com ↗

O que ainda está indefinido

  • Voxtral 3 是否会像 Mistral 其他模型一样最终开放权重?目前仅确认为公开预览且无开源计划。
  • 在低延迟要求极高的实时通话场景中,Voxtral 如何缩小与 Gemini 3.5 Realtime 的准确率差距?
  • Pro Voice 功能仅需30分钟音频即可克隆说话人风格,其在版权和伦理合规方面的具体限制条款尚未详细披露。

Também nesta thread

  • French AI Firm Mistral Releases New Open Model Mistral Large 4: Claims Leadership in Cybersecurity and Finance2026-10-21
  • French AI firm Mistral releases Voxtral 3: Supporting 50+ language transcription and real-time agent development2026-10-21
Ler o tópico completo →
Continuar pesquisando →