ComfyUI-VoxCPMTTS and ComfyUI-lethris-dia2
Both tools are competitors, providing different implementations for integrating Text-to-Speech (TTS) functionality into ComfyUI, with "A" focusing on the VoxCPM 1.5 model for high-quality speech generation and voice cloning, and "B" utilizing the Dia2 TTS model to generate speech, timestamps, and captions.
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.
This tool helps content creators, marketers, and educators generate natural-sounding speech from text or clone existing voices for audio content. You provide written text and optionally a voice recording, and it produces high-quality audio narration or speech that mimics the cloned voice. It's designed for anyone needing realistic spoken audio without hiring voice talent or specialized recording equipment.
About ComfyUI-lethris-dia2
lord-lethris/ComfyUI-lethris-dia2
ComfyUI custom nodes for the Dia2 TTS model — generate speech, timestamps, and captions directly inside ComfyUI.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work