Piotr Dabkowski · ElevenLabs 作者页 · 2025-06-03精选模型评分72
ElevenLabs 发布 Eleven v3（alpha）语音模型
Introducing Eleven v3 (alpha)
导读
ElevenLabs 发布 Eleven v3（alpha）文本转语音模型，支持 70 多种语言、多说话人对话，以及用 [excited]、[whispers] 等音频标签控制语气和情绪。
推荐理由
原文列出音频标签、多说话人对话和70多种语言等能力，并说明实时场景仍建议用旧版，读者可据此判断适用边界。
分类置信度
高
- 官方或准官方来源，且无冲突类别。
- 正文、可信日期、主分类和证据摘录完整。
来源级别：官方账号与准官方
事件类型：研究发布
证据摘录
- “We're pleased to reveal Eleven v3 (alpha) — the most expressive Text to Speech model .”
- “Eleven v3 is available today on our website and in the API .”
- “For real-time and conversational use cases, we recommend staying with v2.5 Turbo or Flash for now.”
- “Professional Voice Clones (PVCs) are currently not fully optimized for Eleven v3, resulting in potentially lower clone quality compared to earlier models.”
- “API access and support in Studio are coming soon.”
来源：Piotr Dabkowski · ElevenLabs 作者页 · elevenlabs.io