Add Tts Model

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration. Use when adding a new TTS model, wiring stage separation for speech synthesis, enabling online voice generation serving, debugging TTS integration behavior, or building audio output pipelines.

krafton-ai Updated
vllm-omni

File contents

krafton-ai/vllm-omni commit 811a359d0e

Frequently asked questions

npx get-skill add krafton-ai/add-tts-model