Fish Audio Drama 3 lands in vLLM-Omni: 128 concurrent streams on one H200
vllm_project · x · 2026-10-15
vLLM announced that Fish Audio's Drama 3 voice model is now supported in vLLM-Omni, offering voice cloning, speaker tags, and expressive delivery via /v1/audio/speech with streaming 44.1 kHz audio.
- The model has 35B total parameters with 3B active per token
- The merged optimization PR reports 128 concurrent streams on a single H200, with a 255 ms median time to first audio and 222.2 seconds of audio generated per second
- Both stages share the GPU; benchmarks average 5 runs of 1,088 Seed-TTS-Eval English requests each, using pre-encoded voice references
Try it on current upstream: vllm serve fishaudio/drama-3 --omni --port 8091.
More from Infra
- patio11 on multi-agent dev: clearly the future, and we'll buy so much inference — IgorCarron · 2026-10-15
- Hugging Face Hub makes model tensor inspection up to 20x faster, DeepSeek-V3.2 drops from 9.2s to 0.45s — victormustar · 2026-10-15
- RTX 5060 Ti 16GB surges up to 144% in Japan, hitting $1,292 as RTX 5080 tops $2,400 — chemist_slime · 2026-10-15
- 1,174 Macs form Darkbloom inference network, growing 4.5x in 60 days at half the cost — gajesh · 2026-10-15
- ByteDance in advanced talks with MediaTek for custom AI data-center chips, Bloomberg reports — mark_k · 2026-10-15
- Decision Models mining to support smaller models, even CPU-only like Laya — airesearch12 · 2026-10-15