ComfyUI TTS for Openclaw

A specialized text-to-speech utility that interfaces with ComfyUI's Qwen-TTS service to generate high-quality audio files.

yhsi5358
v1.0.0
Feb 14, 2026
0
2.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install comfyui-tts

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install comfyui-tts using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is ComfyUI TTS?

The ComfyUI TTS skill is a powerful extension for developers looking to integrate advanced voice generation into their automated workflows. By leveraging the Qwen-TTS model through a ComfyUI backend, this tool allows for the creation of expressive, natural-sounding speech from plain text. It is a perfect example of how Openclaw Skills can bridge the gap between AI coding environments and complex media generation pipelines.

This skill provides a programmatic interface to handle everything from model selection to fine-tuning voice characteristics like emotion and character type. Whether you are building an interactive AI agent or a batch processing script, this skill simplifies the API interaction with ComfyUI, providing a reliable CLI-based approach to audio production.

ComfyUI TTS Use Cases

  • Narrating automated technical documentation or blog posts into audio format.
  • Creating character-specific voice lines for gaming or interactive storytelling.
  • Generating localized speech for internationalized applications using various Qwen-TTS models.
  • Integrating high-fidelity text-to-speech capabilities into Openclaw Skills based AI agents.

How ComfyUI TTS Works

  1. The skill captures the input text and configuration parameters such as voice character, style, and model size.
  2. It dynamically constructs a ComfyUI workflow JSON object tailored to the Qwen-TTS node requirements.
  3. The workflow is submitted to the ComfyUI server via the /prompt API endpoint.
  4. The skill continuously polls the /history endpoint to track the execution status of the generation job.
  5. Upon completion, the script identifies the output file location and returns the path to the generated .wav file.

ComfyUI TTS Setup

To use this skill, ensure you have curl and jq installed. You must have a running instance of ComfyUI with the Qwen-TTS nodes installed.

Configure your environment variables:

export COMFYUI_HOST="localhost"
export COMFYUI_PORT="8188"
export COMFYUI_OUTPUT_DIR="/path/to/outputs"

Run the generation script:

scripts/tts.sh "Your text here" --character "Girl" --style "Emotional"

ComfyUI TTS Data Schema & Taxonomy

The skill interacts with ComfyUI using the following data structure for parameters and outputs:

Parameter Type Description
text String The input text to be converted to audio.
character String The voice profile (e.g., Girl, Boy).
model String The Qwen-TTS model size (0.5B, 1.7B, 3B).
temperature Float Controls the randomness of the speech generation (0.0 - 1.0).
output_path String The filesystem path where the resulting .wav is stored.

ComfyUI TTS Advanced Features

  • Multi-model support allowing users to switch between 0.5B, 1.7B, and 3B versions for performance optimization.
  • Fine-grained control over sampling via temperature, top-p, and top-k parameters for varied vocal textures.
  • Seamless integration with existing Openclaw Skills automation for end-to-end content production.
  • Customizable speaking styles to provide emotional context to the generated speech.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0