Meta发布实时音频模型Muse Voice Transcribe
Meta's new real-time audio model is the foundation for AI assistants that never stop listening
Meta出了个能实时转录语音的模型，80毫秒响应速度，还能区分说话者，价格还最低。
Meta Superintelligence Labs推出Muse Voice Transcribe模型，能以80毫秒为单位处理语音流。该模型可区分不同说话者并检测句子边界。据Artificial Analysis评估，它提供市场上最准确的流式转录服务且价格最低。Meta视其为构建持续监听对话的AI助手的基础组件。
Meta's new real-time audio model is the foundation for AI assistants that never stop listening
Meta's Superintelligence Labs have released Muse Voice Transcribe, a real-time transcription model that processes speech in 80-millisecond chunks, tells speakers apart, and detects sentence boundaries. According to Artificial Analysis, it delivers the most accurate streaming transcription at the lowest price in the market. Meta sees the model as a building block for personal AI agents that listen in on real conversations through devices like its camera glasses. The article Meta's new real-time audio model is the foundation for AI assistants that never stop listening appeared first on The Decoder .
