Mistral AI 发布 Voxtral 3，全语音智能体堆栈实时听、思考和说话
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI 发布了新的语音智能体堆栈 Voxtral 3，包括语音转文本、文本转语音模型和基于 LiveKit 的语音智能体 SDK。支持超过 50 种语言的转录和超过 35 种语言的文本转语音输出，支持情感适应。智能体可以在实时对话中访问外部系统。
原文给出了能力变化和开放入口，读者可以据此判断它会怎样改变现有工作流。
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.
来源：The Decoder · the-decoder.com