ElevenLabs 发布 Eleven Realtime 两款语音到语音模型，主打实时对话
Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations
ElevenLabs 出了个语音转语音模型 v1 Max，0.57 秒就回话，Big Bench Audio 跑分 98.8%，做语音对话的可以看看。
ElevenLabs 推出 Eleven Realtime 系列语音到语音模型，包含 v1 Max 等两个变体，面向实时 AI 对话场景。其中 v1 Max 在 Big Bench Audio 基准上拿到 98.8% 的成绩，响应时间为 0.57 秒。ElevenLabs 称在 Artificial Analysis 排行榜上没有模型能同时做到更快和更准。该系列强调速度与准确率兼顾，适合语音智能体等低延迟需求。
Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations
Elevenlabs' new Eleven Realtime speech-to-speech models combine speed and accuracy. The v1 Max variant scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time. Elevenlabs says no model on the Artificial Analysis leaderboard is both faster and more accurate. The article Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations appeared first on The Decoder .
