Meta 发布实时音频模型 Muse Voice Transcribe，支持多说话人识别
原标题：Meta's new real-time audio model is the foundation for AI assistants that never stop listening
AI 摘要
Meta 的超级智能实验室发布了首个实时音频感知模型 Muse Voice Transcribe，能够实时转写语音、区分说话人并检测句子边界。该模型将音频分成 80 毫秒的块，并根据难度动态调整延迟，以平衡速度和准确性。其定价为每小时 0.18 美元，低于 OpenAI 和 ElevenLabs 等竞争对手，支持超过 70 种语言，现已通过 Meta AI 和 Meta Model API 提供。
正文节选
Meta's new real-time audio model is the foundation for AI assistants that never stop listening Key Points - Meta has released Muse Voice Transcribe, a real-time model that transcribes speech, detects sentence boundaries, and tells up to 20 speakers apart without separate systems. - The model breaks audio into 80-millisecond chunks and adjusts the delay for each word based on difficulty, balancing speed and accuracy on the fly. - At $0.18 per hour, Meta undercuts competitors like OpenAI and Eleve