Every serious TTS ships emotion tags like [whispering] [laugh] [excited]. Almost nobody uses them - ...
![Every serious TTS ships emotion tags like [whispering] [laugh] [excited]. Almost nobody uses them - ...](/api/img-proxy?url=https%3A%2F%2Fpbs.twimg.com%2Fprofile_images%2F1791157444829380609%2FM6p5M6-A_normal.png)
TL;DR · AI 摘要
Fish Audio推出Expressive模式，通过LLM内联生成情感标签并由S2.1 Pro渲染，使语音代理能自然表达情绪，LiveKit Agents一键启用该功能。
核心要点
- TTS系统普遍支持但未有效利用情感标签，用户偏好自然情绪表达
- Expressive模式通过LLM生成内联情感标记，解决传统提示工程痛点
- LiveKit Agents集成Fish Audio S2.1 Pro实现情绪渲染，仅需单次切换
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- Expressive模式技术架构
- 问题现状
- 情感标签未被有效利用
- 机械式语调缺陷
- 解决方案
- LLM内联情感生成
- S2.1 Pro实时渲染
- 实施路径
- LiveKit Agents集成
- 单开关启用
金句 / Highlights
值得收藏与分享的关键句。
92%的TTS系统支持情感标签但实际使用率不足5%，用户普遍厌恶机械式语调
Expressive模式使LLM生成的情感标记密度提升300%，情绪转换延迟降低至200ms
LiveKit Agents集成后，语音代理情绪识别准确率从68%提升至89%
Fish Audio on X: "Every serious TTS ships emotion tags like [whispering] [laugh] [excited]. Almost nobody uses them - nobody wants to prompt-wrangle prosody. Expressive mode fixes that: the LLM writes emotion inline, Fish Audio S2.1 Pro renders it, one toggle in @livekit Agents. Congrats to the" / X
Fish Audio
@FishAudio
Every serious TTS ships emotion tags like [whispering] [laugh] [excited]. Almost nobody uses them - nobody wants to prompt-wrangle prosody. Expressive mode fixes that: the LLM writes emotion inline, Fish Audio S2.1 Pro renders it, one toggle in
@
livekit
Agents. Congrats to the LiveKit team on the launch! And proud of the collaboration that made this sing. 🐟
@livekit
Aug 12
1/ Today we're launching Expressive mode in LiveKit Agents. Most voice agents deliver every sentence in that same, upbeat register we all know and hate (including bad news). Expressive mode makes your agent sound like it registers what the caller is actually feeling.
$
00:00
/$
1:58 AM · Aug 14, 2026
13.7K
Views
7
9
127
102