ComfyUI-VibeVoice and ComfyUI-VoxCPM
These are complementary TTS tools that serve different use cases—VibeVoice excels at multi-speaker conversational audio while VoxCPM specializes in zero-shot voice cloning—so users might employ both depending on whether they need expressive dialogue generation or speaker-specific voice synthesis.
About ComfyUI-VibeVoice
wildminder/ComfyUI-VibeVoice
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
Integrates Microsoft's VibeVoice model directly into ComfyUI workflows for multi-speaker dialogue generation, supporting voice cloning via reference audio and hybrid zero-shot voice generation. Features 4-bit LLM quantization, multiple attention backends (eager/SDPA/Flash Attention/SageAttention), and automatic model management with configurable diffusion parameters for fine-grained control over speech synthesis.
About ComfyUI-VoxCPM
wildminder/ComfyUI-VoxCPM
ComfyUI node for highly expressive speech and realistic zero-shot voice cloning
Implements a tokenizer-free diffusion-based TTS architecture built on MiniCPM-4 that models speech in continuous space rather than discrete tokens, enabling context-aware prosody generation. Includes native LoRA fine-tuning support within ComfyUI for custom voice style training, automatic model management with efficient VRAM offloading, and operates at 6.25Hz token rate for faster synthesis on consumer hardware. Integrates seamlessly with ComfyUI's node workflow system, supporting optional reference audio for voice cloning and compatible with multiple inference backends (CUDA, CPU, MPS, DirectML).
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work