Mistral 发布 Voxtral 3 音频模型家族与 Voice Agents

AI 摘要

Mistral 发布 Voxtral 3 音频模型家族，包含四个语音转文字与文字转语音模型，均处于公开预览阶段。其中 Voxtral TTS 3 支持零样本声音克隆、流式与上下文感知播报，另外三个转写模型覆盖离线转写、说话人分离与实时转写。Mistral 同时推出 Voice Agents 托管实时双向语音管线，并通过 Voice Agents SDK 提供电话、浏览器与自定义音频接口。

正文节选

We released the Voxtral 3 audio family, our next generation of speech-to-text and text-to-speech models. All four models are in Public Preview. See the Voxtral 3 announcement and the audio models pricing. MODEL RELEASED Voxtral TTS 3 ( voxtral-mini-tts-3-0 ): text-to-speech with zero-shot voice cloning, streaming, and contextual delivery. See the model card. Voxtral Mini Transcribe 3 ( voxtral-mini-transcribe-3-0 ): offline transcription and diarization with timestamps. See the model card. Voxtr

发布时间：—

抓取时间：2026-10-23 00:00

来源机构：Mistral AI