RVC

ComfyUI-RVC

dependency-free Retrieval-based Voice Conversion (RVC) for ComfyUI. Inference only — no training, no index building.

Models

Download the base assets from Aero-Ex/ComfyUI-RVC on Hugging Face and place them in ComfyUI/models/rvc/. The three base assets are Comfy-format safetensors; voices are used directly from upstream .pth.

| File | What it is | | --- | --- | | hubert_base.safetensors | ContentVec-500 content encoder | | rmvpe.safetensors | RMVPE pitch estimator | | fcpe.safetensors | FCPE pitch estimator (fast) | | <voice>.pth | An RVC voice model |

hubert_base.safetensors, rmvpe.safetensors and fcpe.safetensors are converted from the upstream .pt files with the pack's offline converter. Voice .pth files are RVC checkpoints with the keys weight, config, info, sr, f0, version — put them in the same folder, no conversion needed.

The RVC voice file is the one thing you must supply yourself. Any RVC v1 or v2 model from a voice-model sharing site works. Do not use a raw training checkpoint (G_*.pth / D_*.pth with only model) — the loader requires the RVC wrapper format above and will reject it.

Workflow

Load RVC Hubert ─────────┐
Load RVC Pitch (RMVPE) ──┼─→ RVC Convert ─→ Save Audio
Load RVC Voice ──────────┘        ↑
                              Load Audio

1. Load RVC Hubert — pick hubert_base.safetensors.
2. Load RVC Pitch (RMVPE/FCPE) — pick rmvpe.safetensors or fcpe.safetensors.
3. Load RVC Voice — pick your voice .pth.
4. Load Audio — any source audio. Stereo and arbitrary sample rates are handled for you (resampled to 16 kHz mono internally).
5. RVC Convert — connect the three models and the audio.
6. Feed the output into Preview Audio or Save Audio.

Node inputs

Loaders

Load RVC Hubert, Load RVC Pitch, each take a filename from models/rvc/.

RVC Convert

| Input | Default | Notes | | --- | --- | --- | | f0_up_key | 0 | Pitch shift in semitones, −24…24. | | speaker_id | 0 | Speaker slot for multi-speaker voices. Range auto-clamps to the voice. | | index_rate | 0.75 | Retrieval blend strength. Only used when an index is connected. | | protect | 0.33 | Upstream's consonant protection: frames at 0 Hz keep only this share of the index-retrieved features. Like upstream, unvoiced frames are interpolated first, so it only acts when no frame is voiced. 0.5 disables it. | | rms_mix_rate | 1.0 | Volume-envelope matching against the input. 1.0 = off. | | resample_sr | 0 | Output sample rate. 0 keeps the voice's own rate. | | seed | 0 | Seed for the voice's latent and excitation noise. Same seed, same output. |

The pitch estimator is whichever model is connected to pitch. Connecting a second one to pitch_model_b averages the two where both hear a voiced frame.

Notes

• Output is sampled. RVC draws latent noise at inference; the seed input fixes it, so a seed always gives the same conversion.
• VRAM is managed by ComfyUI's dynamic loader. All three base models plus a voice run comfortably on a 6 GB card at fp16.
• Sample rate of the output is the voice model's native rate unless resample_sr is set. Upstream uses librosa.resample; this pack uses comfy.audio.resample so it matches the rest of ComfyUI's audio handling.

ComfyUI-RVC