Mistral AI 发布 Voxtral 3 全栈实时语音智能体
原标题：Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
AI 摘要
Mistral AI 发布 Voxtral 3 语音智能体模型系列，包含语音转文字模型 Voxtral Small Transcribe 3、文字转语音模型 Voxtral Mini TTS 3，以及基于 LiveKit 的语音智能体 SDK。该系列将聆听、思考、工具调用与说话整合为单一流式管线，转写支持 50 多种语言，语音合成支持 35 种以上语言和 50 种方言并具备情感适配，智能体可在实时对话中接入外部系统。系统可部署在自有基础设施或欧盟托管 API 上，转写定价为每分钟 0.0035 美元起。
正文节选
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time Mistral AI has launched Voxtral 3, a new family of language models built for real-time voice agents. The system includes a speech-to-text model (Voxtral Small Transcribe 3), a text-to-speech model (Voxtral Mini TTS 3), and a voice agent SDK based on LiveKit. Together, they combine listening, thinking, tool use, and speaking into a single streaming pipeline. Transcription covers more than 50 langu