AI 导读
Meta 旗下 MSL 的 Muse Voice Transcribe 模型已在 Meta models API 上线，主打流式语音转文字的 SOTA 表现，训练覆盖 70 多种语言。引用信息显示，该模型已在 Meta 桌面应用中承担听写、在 Muse Code 中承担语音输入，API 提供零数据留存档位。
正文
META 🔥: A new Muse Voice Transcribe model from MSL is now available on Meta models API.
> SOTA in streaming speech-to-text.
> Trained on 70+ languages.
As it has been foretold 👀 https://t.co/ZyMxJhVfnO https://t.co/de6AbAwAPr
Already powering dictation in the Meta desktop app and voice input in Muse Code. Live now on the Meta model API with a zero-data-retention tier. https://t.co/sppqZ0OSXz在 X 查看被引用的帖子
来源：@testingcatalog · x.com