eigenpunk/ComfyUI-audio
some generative audio tools for ComfyUI
Provides multiple specialized generative audio models (Tacotron2, VALL-E X, Tortoise, MusicGen, AudioGen) as ComfyUI nodes, enabling text-to-speech, text-to-music, and audio continuation workflows. Wraps established research implementations (NVIDIA's Tacotron2, Meta's AudioCraft, community forks) with audio utility nodes for conversion and export. Targets GPU-accelerated inference on CUDA 12.1/11.8, though primarily tested on Linux.
101 stars. No commits in the last 6 months.
Stars
101
Forks
20
Language
Python
License
GPL-3.0
Category
Last pushed
Aug 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/eigenpunk/ComfyUI-audio"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
diodiogod/TTS-Audio-Suite
A ComfyUI custom node integration for multi-engine multi-language Text-to-Speech and Voice...
Enemyx-net/VibeVoice-ComfyUI
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling...
wildminder/ComfyUI-VibeVoice
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
1038lab/ComfyUI-EdgeTTS
ComfyUI-EdgeTTS is a powerful text-to-speech node for ComfyUI, leveraging Microsoft's Edge TTS...
wildminder/ComfyUI-VoxCPM
ComfyUI node for highly expressive speech and realistic zero-shot voice cloning