zsxkib / create-rvc-dataset

Create your own Realistic Voice Cloning (RVC v2) dataset using a YouTube link

Run with an API
Playground API Examples README Versions

Input

*string
Shift + Return to add a new line

URL to YouTube video you'd like to create your RVC v2 dataset from

string
Shift + Return to add a new line

Name of the dataset. The output will be a zip file containing a folder named `dataset/<audio_name>/`. This folder will include multiple `.mp3` files named as `split_<i>.mp3`. Each `split_<i>.mp3` file is a short audio clip extracted from the provided YouTube video, where voice has been isolated from the background noise.

Default: "rvc_v2_voices"

Add a payment method to run this model.

Each run costs approximately$0.06. Alternatively, try out our featured models for free.

Sign in with GitHub

By signing in, you agree to our
terms of service and privacy policy

Output

dataset_andrew_huberman.zip
Generated in
Tweak itReport

This example was created by a different version, zsxkib/create-rvc-dataset:f6593d27.

Run time and cost

This model costs approximately $0.060 to run on Replicate, or 16 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 83 seconds. The predict time for this model varies significantly based on the inputs.

Readme

RVC v2 Dataset Creation Tool

Introduction

Create vocal datasets for Realistic Voice Cloning (RVC) v2 models with ease. Simply provide a YouTube video URL and let the tool handle the extraction and preparation of vocal data, ideal for training sophisticated voice cloning models. 🧠🎤

Features

  • Easy Input: Paste the URL and optionally name your dataset. 📌
  • Automated Processing: Isolates vocals and segments them into clips. ⚙️
  • Immediate Download: Access your dataset with a click. 💾

How to Use

  1. YouTube URL: Input the link to the video. 🖇️
  2. Dataset Name: Choose a name or stick with the default. ✏️
  3. Run: Hit ‘Run’ to begin the magic. 🚀
  4. Download: Grab your .zip file full of vocal clips. 📦

What You Get

  • The output is a .zip file titled dataset/<your_dataset_name>/.
  • It houses split_<i>.mp3 files, each containing a clear vocal extract. 🎶

Training Your Model

Once you have your dataset, head over to https://replicate.com/zsxkib/train-rvc-v2 to train your RVC v2 model on your newly created dataset. 🚀

Acknowledgments

This tool is adapted from work by the talented ardha27, who authored the initial codebase available here. 🙏