Fish Audio Drama 3 is now supported in vLLM-Omni

What happened

Fish Audio Drama 3 is now supported in vLLM-Omni, offering voice cloning, speaker tags, expressive delivery through /v1/audio/speech, and streaming 44.1 kHz audio. 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 current upstream: vllm serve fishaudio/drama-3 --omni --port 8091 Recipe: https://github.com/vllm-project/vllm-omni/blob/main/recipes/fishaudio/Drama-3.md

The story so far

vLLM has added support for Fish Audio Drama 3 in vLLM-Omni, making voice cloning, speaker tags and expressive delivery available through the /v1/audio/speech endpoint with streaming 44.1 kHz audio. The model has 35B total parameters, with 3B active per token, and can now be served using the current upstream version. The merged optimization pull request reports 128 concurrent streams on a single H200 GPU, with a median time to first audio of 255 ms and throughput of 222.2 seconds of audio generated per second. Those results were averaged over five runs of 1,088 Seed-TTS-Eval English requests each, using pre-encoded voice references and running both stages on the same GPU.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights