ComfyUI-KittenTTS and ComfyUI-VoxCPMTTS
These two custom nodes are competitors, both offering Text-to-Speech (TTS) functionality within ComfyUI, but leveraging different underlying TTS models: KittenTTS for lightweight, and VoxCPM 1.5 for high-quality speech generation and voice cloning.
About ComfyUI-KittenTTS
Saganaki22/ComfyUI-KittenTTS
😻 A simple ComfyUI custom node for KittenTTS - an ultra-lightweight text-to-speech model. Works on CUDA and CPU.
Wraps KittenTTS models (19–80MB) as a single ComfyUI node with automatic model caching and dynamic ONNX Runtime selection for CPU/GPU inference. Features phoneme-based synthesis via espeak-ng, 8 voice options, adjustable speech speed, and optional stereo output, with models ranging from nano-int8 quantization to 80M parameter variants for quality-performance tradeoffs.
About ComfyUI-VoxCPMTTS
1038lab/ComfyUI-VoxCPMTTS
A clean, efficient ComfyUI custom node for VoxCPM TTS (Text-to-Speech) functionality. This implementation provides high-quality speech generation and voice cloning capabilities using the VoxCPM 1.5 model.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work