vLLM-Omni 支持 Fish Audio Drama 3 语音模型
vLLM-Omni 现在能跑 Fish Audio 的 Drama 3 了，单卡 H200 就能带 128 路并发语音流，想做语音克隆服务的可以上手试试。
vLLM-Omni 上线了 Fish Audio 的 Drama 3 模型，支持语音克隆、说话人标签和富有表现力的朗读，通过 /v1/audio/speech 接口提供 44.1 kHz 流式音频。该模型总参数量 35B，每个 token 激活 3B。官方优化 PR 显示，单张 H200 可承载 128 路并发流，音频首包延迟中位数为 255 毫秒，每秒可生成 222.2 秒音频。测试基于 5 轮、每轮 1088 条 Seed-TTS-Eval 英文请求，两个阶段共享同一 GPU。
🎉 Fish Audio Drama 3 is now supported in vLLM-Omni!
Voice cloning, speaker tags and expressive delivery through /v1/audio/speech, with streaming 44.1 kHz audio. The model has 35B total parameters and 3B active per token.
The merged optimization PR reports 128 concurrent streams on one H200: 255 ms median time to first audio and 222.2 seconds of audio generated per second. Both stages share the GPU; averaged over 5 runs of 1,088 Seed-TTS-Eval English requests per run, with pre-encoded voice references.
Try it on current upstream: vllm serve fishaudio/drama-3 --omni --port 8091
Thanks to Fish Audio and the vLLM-Omni contributors! Recipe: https://t.co/2J80SEoKuJ
