ComfyUI Extension: ComfyUI-Text2Speech
A ComfyUI custom node for text-to-speech integration with a local TTS server.
Custom Nodes (0)
README
ComfyUI-Text2Speech
A ComfyUI custom node for text-to-speech integration with a local TTS server.
Features
- Custom ComfyUI node
HttpTTSToAudiofor sending text to a local TTS server. - Option to load text from a file.
- Server status check node
TTSServerStatus. - Local TTS server using pyttsx3 (offline TTS engine), outputs MP3 files.
- Easy setup with batch files for Windows.
Prerequisites
- Python 3.8+ installed and added to PATH. Download from python.org.
Installation
TTS Server Setup
- Run
install.batto create a virtual environment and install dependencies. - Run
run_tts.batto start the TTS server onhttp://127.0.0.1:5002.
ComfyUI Node
- The
__init__.pyfile is already in thecustom_nodesfolder. - Restart ComfyUI.
Usage
- Use the
HttpTTSToAudionode in ComfyUI undergeekatplay/TTSto generate speech from text or a text file. - Use the
TTSServerStatusnode to check if the server is running. - Input text, optional text file path, language, and server URL.
- Output is the path to the generated MP3 audio file.
Workflow
Connect the audio path to audio/video processing nodes in ComfyUI for creating TTS-enhanced content.