ComfyUI-VibeVoice and ComfyUI-SparkTTS

These are complementary TTS nodes that serve different use cases—VibeVoice excels at expressive, conversational multi-speaker audio while SparkTTS leverages LLM-based synthesis for naturalness—allowing users to choose or combine them based on their specific audio generation needs within ComfyUI.

ComfyUI-VibeVoice
50
Established
ComfyUI-SparkTTS
41
Emerging
Maintenance 2/25
Adoption 10/25
Maturity 15/25
Community 23/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 13/25
Stars: 563
Forks: 105
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 124
Forks: 13
Downloads:
Commits (30d): 0
Language: Python
License: GPL-3.0
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About ComfyUI-VibeVoice

wildminder/ComfyUI-VibeVoice

ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio

This tool helps content creators, podcasters, and educators generate natural-sounding, multi-speaker audio conversations from a written script. You provide a text dialogue and optionally some reference audio clips for specific voices, and it produces a single audio file with up to four distinct, expressive speakers. It's designed for anyone who needs high-quality, long-form conversational audio without recording multiple people.

podcasting audiobook creation content generation e-learning development dialogue synthesis

About ComfyUI-SparkTTS

1038lab/ComfyUI-SparkTTS

ComfyUI-SparkTTS is a custom ComfyUI node implementation of SparkTTS, an advanced text-to-speech system that harnesses the power of large language models (LLMs) to generate highly accurate and natural-sounding speech.

This tool helps content creators, educators, or marketers generate natural-sounding speech from text using advanced AI. You provide text and, optionally, a reference audio sample, and it produces high-quality audio in a customized or cloned voice. It's designed for anyone needing realistic voiceovers or personalized audio content.

voice-generation audio-content-creation narration podcast-production e-learning

Scores updated daily from GitHub, PyPI, and npm data. How scores work