vllm-omni-audio-tts

Community

Multi-model audio: TTS, voice cloning.

Authorhsliuustc0106
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Generate multi-model audio content and TTS outputs by orchestrating Qwen3-TTS, MiMo-Audio, and Stable-Audio within vLLM-Omni, simplifying cross-model workflows for speech and sound generation.

Core Features & Use Cases

  • TTS & Voice Cloning: Convert text to realistic speech including cloning voices from reference samples.
  • Voice Design & Audio Generation: Design unique voice personas and compose audio with music and sound effects.
  • Use Case: Create a narrated video with a cloned presenter voice and synchronized background music using a single API.

Quick Start

Provide a text prompt and select a model to generate speech or audio using Omni.

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: vllm-omni-audio-tts
Download link: https://github.com/hsliuustc0106/vllm-omni-skills/archive/main.zip#vllm-omni-audio-tts

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 223,000+ vetted skills library on demand.