add-tts-model

Official

Production-ready TTS integration for vLLM-Omni.

Authorvllm-project
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation to enable production-ready, streaming audio serving with CUDA graph acceleration and robust deployment workflows.

Core Features & Use Cases

  • HF reference integration for TTS models (two-stage and single-stage patterns)
  • Stage separation, online serving, and async chunk streaming with low-latency audio
  • CUDA graph acceleration and pre-commit / DCO workflow for production-grade deployments
  • Use Case: rapid integration of a new TTS model to a live service with end-to-end testing

Quick Start

Wiring a HuggingFace TTS model into vLLM-Omni for production-ready streaming audio.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: add-tts-model
Download link: https://github.com/vllm-project/vllm-omni/archive/main.zip#add-tts-model

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.