Skip to content
Audio

Phrolova English Voice

RVC v2

1 min readupdated

A new RVC v2 voice conversion model (Retrieval-based Voice Conversion technology for timbre transfer) transfers singing or speech to the English voice of Phrolova from the game Wuthering Waves. The tool processes a prepared isolated vocal track, replacing the original timbre with the character's voice voiced by Rae Lim. Trained on 48 minutes of clean audio, the model is designed for creating covers and redubbing.

Key features

  • RVC v2 architecture at 48/40 kHz with a HiFi-GAN vocoder
  • RMVPE pitch extraction algorithm for precise analysis
  • Full 446 MB feature retrieval index
  • 20 checkpoints at 10-epoch intervals to find the optimal sound

What you can do

  • Create a vocal cover with the character's English voice
  • Redub existing speech recordings or dialogues
  • Select a checkpoint (for example, between the 150th and 200th epochs) for a specific track

Example

To run in Applio, prepare an isolated dry vocal track (without music or heavy reverb), select the RMVPE algorithm, and start with a zero semitone pitch shift.

Read moreDetails
Architecture: RVC v2, ContentVec, RMVPE
Dataset: 733 files, about 47.8 minutes of audio
Training: Applio, 200 epochs, 34,600 steps
Requirements: NVIDIA graphics card with Applio support
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.1 GB · ready files0.6 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Richopera/phrolova-en-rvc-v2
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Richopera/phrolova-en-rvc-v2 --local-dir ~/models/phrolova-en-rvc-v2
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to phrolova-en-rvc-v2
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

  1. VoiceConversionWebUIfamily root
  2. Applio
  3. phrolova-en-rvc-v2

New posts about versions of VoiceConversionWebUI (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 5All on Hugging Face

About the model

Richopera/phrolova-en-rvc-v2
Author
Richopera
Category
Audio
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments