Mistral AI 发布 Voxtral 3 实时语音智能体全套件
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
AI 导读
Mistral AI 发布 Voxtral 3，一套面向实时语音智能体的模型家族，包含语音转写模型 Voxtral Small Transcribe 3、语音合成模型 Voxtral Mini TTS 3，以及基于 LiveKit 的语音智能体 SDK，把听、思考、工具调用和说话整合进同一条流式流水线。
摘要与补充说明
转写覆盖 50 多种语言，语音合成支持 35 种以上语言和 50 种方言，并带情感适配；智能体可在实时对话中调用外部系统，例如预约或查询发票。Mistral 称系统可部署在自有基础设施或通过欧盟托管的 API 运行，转写价格从每分钟 0.0035 美元起。
正文
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 languages. Text-to-speech output supports over 35 languages and 50 dialects with emotional adaptation. Agents can tap into external systems during live conversations, for example, to book appointments or check invoices.
Mistral says the system can run on your own infrastructure or through EU-hosted APIs to keep data under your control. Pricing starts at $0.0035 per minute for transcription. More details are in the documentation.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.