ElevenLabs 发布 Eleven v4 情感语音模型及 Turbo 低延迟版
原标题：Introducing Eleven v4, our most emotive model
AI 摘要
ElevenLabs 发布其最具情感表现力的文本转语音模型 Eleven v4 及低延迟版本 Eleven v4 Turbo。Eleven v4 被 Artificial Analysis 评为第一，在盲测中约 75% 听众更偏好该模型，支持超过 90 种语言、更精准的音频标签与 IPA 音素控制，并提升多说话人对话一致性与语音克隆相似度。Eleven v4 Turbo 面向智能体等低延迟场景，中位首语音延迟约 150ms，并与 ElevenAgents 平台协同优化。
正文节选
A line of text can change significantly depending on how it’s spoken. “I need you to stay calm" should sound different depending on who's saying it, whether that's a doctor delivering it gently to a frightened patient, or a character in a game shouting to his squad before dropping into battle. Today we're launching Eleven v4, our most emotive text-to-speech model yet, and its low-latency variant, Eleven v4 Turbo. Ranked #1 by Artificial Analysis1, and preferred by ~75% of listeners in blind head