LMSYS:Blog(Chatbot Arena 团队)·· 12 小时前AI 评分59
Higgs Audio v3 TTS 在 SGLang-Omni 上实现端到端实时语音服务
Blog Higgs Audio v3 TTS on SGLang-Omni: Real-Time, Controllable Speech for Voice Agents Today we are announcing end-to-end serving for Higgs Audio v3 TTS on SGLang-Omni. Higgs Audio v3 TTS is Boson AI's text-to-speech model for conversational voice agents: it generates natural and expres... Boson AI & SGLang-Omni Team June 4, 2026
AI 导读
SGLang-Omni 团队宣布为 Boson AI 的 Higgs Audio v3 TTS 提供端到端推理服务。该模型约 4B 参数,基于 Qwen3-4B 骨干,支持流式合成和 100 种语言的个位数 WER/CER,开发者可通过文本流内嵌控制标签调节情绪、风格、韵律和音效。
来源:LMSYS:Blog(Chatbot Arena 团队) · lmsys.org