▷ About

VoxCPM models speech in a continuous space using a MiniCPM-4 backbone, producing highly expressive speech and accurate zero-shot voice cloning. This node handles model downloading, memory management, and audio processing end-to-end.

❖ VoxCPM2

• Voice Design — generate voices from natural language descriptions
• Controllable Voice Cloning — clone with style control instructions
• Ultimate Cloning — combine reference audio (identity) + prompt audio (prosody)
• 48kHz output, 30+ languages

❖ VoxCPM1.5

• 44.1kHz output, LoRA support, native LoRA training
• Context-aware expressive speech, zero-shot TTS
• Automatic model management

⟔ ▲ ⟓

▓ Getting Started

Via ComfyUI Manager: Search ComfyUI-VoxCPM → Install.

Manual install:

cd ComfyUI/custom_nodes/
git clone https://github.com/wildminder/ComfyUI-VoxCPM.git
cd ComfyUI-VoxCPM
pip install -r requirements.txt

Restart ComfyUI. Nodes appear under audio/tts. Models auto-download to ComfyUI/models/tts/VoxCPM/ on first use.

⟔ ▲ ⟓

▓ Models

⟔ ▲ ⟓

▓ Nodes

❖ VoxCPM TTS

Unified TTS node supporting VoxCPM1.5 and VoxCPM2: zero-shot TTS, voice design, voice cloning, ultimate cloning, LoRA support.

❖ VoxCPM Voice Cloning

Configures audio-based cloning (prompt/reference audio, VAD trimming). Connect to TTS node's voice_config input.

❖ VoxCPM Advanced Params

Configures diffusion parameters (temperature, sway sampling, CFG, timesteps, retry). Connect to TTS node's advanced_params input.

❖ Training Nodes

• VoxCPM Train Config — LoRA training parameters
• VoxCPM Dataset Maker — create training datasets from audio
• VoxCPM LoRA Trainer — train custom LoRA models

Note: voice_design is a direct parameter on the TTS node, not part of the Voice Cloning config.

Config precedence: Direct parameters > config node values > defaults.

⟔ ▲ ⟓

▓ Usage

❖ Basic TTS (Zero-Shot)

Add VoxCPM TTS → select model → enter text → generate.

❖ Voice Cloning (VoxCPM1.5 style)

Connect Load Audio → prompt_audio, provide exact transcript in prompt_text → generate.

❖ Voice Design (VoxCPM2)

Select VoxCPM2 model → enter description in voice_design (e.g., "warm female voice") → generate. Voice design is applied in plain TTS and reference cloning modes. Ignored when prompt audio is used (continuation cloning).

❖ Reference Cloning (VoxCPM2)

Connect reference audio to reference_audio (no transcript needed) → generate. Voice design instructions can be combined with reference audio for controllable cloning (e.g., style control).

❖ Ultimate Cloning (VoxCPM2)

Connect reference_audio (identity) + prompt_audio with transcript (prosody) → generate.

[!NOTE] Denoising: The built-in ZipEnhancer denoiser is disabled by default to keep dependencies light.

⟔ ▲ ⟓

▓ Advanced Parameters

❖ Diffusion

❖ Device & Precision

AudioVAE always runs in FP32 for numerical stability.

❖ VAD (VoxCPM2)

⟔ ▲ ⟓

▓ LoRA Support

Inference: Place .safetensors LoRA files in ComfyUI/models/loras/, refresh, select in lora_name dropdown.

Training: 👉 Full LoRA Training Guide

⟔ ▲ ⟓

▓ Voice Design Examples

Combine descriptions: "warm female voice with slight British accent"

⟔ ▲ ⟓

▓ Voice Cloning Tips

1. Verbatim transcript — prompt_text must match audio word-for-word
2. Punctuation matters — affects intonation
3. 5-15 seconds of clear speech works best

[!Warning] prompt_text is the exact transcript, not a description of the voice.

⟔ ▲ ⟓

▓ Risks and Limitations

• Voice cloning can be misused for deepfakes — use responsibly
• May exhibit instability with very long/complex inputs
• VoxCPM1.5: Chinese and English only; VoxCPM2: 30+ languages

⟔ ▲ ⟓

▓ Changelog

v2.4.0

• Custom model selector UI — replaced default LiteGraph dropdown with custom DOM widget featuring cyber-themed design, SVG model icons, and DEFAULT/CUSTOM badges
• Real-time download progress — live progress bar with cancel support, Xet dedup tracking, and file-level progress
• Lazy-loaded frontend — 95% startup payload reduction; heavy JS loads only when a VoxCPM node is placed
• Model directory dialog — browse and select custom model paths via a dedicated dialog instead of queue-time prompts
• Architecture version tags — model dropdown detects and displays architecture version (v1/v2) tags
• ComfyUI settings API migration — model path settings now use ComfyUI's native settings panel
• Graceful download error handling — automatic retry on transient network errors with toast notifications
• BEM-styled UI — modern CSS architecture with design tokens for consistent theming

v2.3

• VoxCPM2 support (voice design, reference cloning, ultimate cloning, 48kHz, 30+ languages)
• Unified dtype/device handling delegating to ComfyUI
• Vite 5→8 upgrade, LiteGraph canvas widget fixes
• LoRA training nodes

⟔ ▲ ⟓

License

VoxCPM model and components: Apache-2.0 License by OpenBMB.

Acknowledgments

• OpenBMB & ModelBest for VoxCPM
• The ComfyUI team for the platform

⟔ ▲ ⟓

══════════════════════════════════