Powered by

# Voice Models

Last update: July 17, 2025

# What is a Voice Model

  • In the field of AI, is a program that was trained to recognize certain patterns or make certain decisions.

  • In this case, voice models are models trained to replicate a voice, and with AI they apply it to the input audio.

  • There are plenty of them uploaded to the internet, made by the public. And the best way to make them is with RVC.

# ‎

# Voice Model Files

# ‎
# PTH:
  • This file is the model itself.
  • Contains data regarding pitch.
  • While training, RVC generates other .PTHs named D_ and G_, but these are the checkpoints, not usable models.
# ‎
# INDEX:
  • Contains data regarding the voice's accent and speech manner.
  • File is additional, but usually crucial for the quality of the model.
  • While training, RVC generates two .INDEX file, but the right one will be named added_ by default.
# ‎

# How to Search Voice Models

# Five methods to find one online.

# ‎
image
  • This a website where people can upload voice models.
  • Models uploaded in AI Hub get automatically stored here too.
  • Users can read/share feedback about the models through comments & likes.
# ‎

# 1. Log in

  • Access the website here & login by clicking the icon on the top right corner.
# ‎

# 2. Search

  • Type the name of the model in the Search bar & click a result.

    image ‎
    ‎

# ‎

# 3. Evaluate model (optional)

  • Check the description, likes, comments, & audio sample. Feedback can help you know how great the model is.
  • The sample of the gender & vocal style according to the model gives the most accurate representation.

  • This step is specially useful if you get multiple results of the same model.

    image
# ‎

# 4. Download

  • Tap the three dots & Download model. It will download a .ZIP file of it.
    ‎
    image‎
    ‎

  • If you need a link for it, use the other methods.

  • If it only exists in weights.com, download the .ZIP & upload it to HF.
image

‎

  • This is a forum channel in AI Hub where people upload their own voice models.
  • Searching here is specially useful if you need the model as a link, as the posts include one.
# ‎

# 1. Enter the channel

  • If you haven't already, join AI Hub here.
  • Then go to the #voice-models forum channel.
image
# ‎

# 2. Search

  • In the upper search bar, search your model & click the post.
# ‎

# 3. Download

  • Click the Hugging Face link to download the model, or copy it if that's what you need.

  • You can listen to the audio sample to get a preview of the it.

    image
image

‎

  • This is a Discord bot developed by the Weights.com team.
  • It searches the models uploaded on Weights.com/AI Hub Discord server.
  • There's also its web version.
# ‎

# 1. Enter the channel

  • If you haven't already, join AI Hub here.
  • Head over to the #find-models channel.
# ‎

# 2. Type command

  • # In the chat:

    1. Type /find
    2. Select the Weights command
    3. Type the model
    4. Send the message

    ‎

    image
# ‎

# 3. Download

‎ ‎ ‎ ‎ ‎ ‎ image ‎

  • 🔗‎ Click Use Model to Use it on Weights.com.

  • 📤‎ Click View Model to View it, and by being logged in, you can click the 3 dots and Download it.

  • 👀‎ If there are multiple models, click the View other models... bar to see the others.
image

‎

  • This is a free & open-source platform for storing Any Type AI models, interactive AI apps, & datasets.
# ‎

  1. Go to the models page & search the model in the Filter by name bar.

    image‎
    ‎

  2. Click the model & go to the Files and versions tab.

  3. To download it, click the download symbol ( ) on the right of the .ZIP file.
    If you need its link, right-click it and copy the address.

    image
# ‎
# ‎

# If you couldn't find one, you have 3 options:

# ‎

# Uploading to Weights.com

‎
‎

# 1. Zip the model

  • Select the correct .PTH & .INDEX & zip them into a .ZIP file.

  • Ensure it's .ZIP & not .RAR or .7ZIP.

# ‎

# 2. Log in

# ‎

# 3. Upload the Model

  1. Once logged in, go to Upload a Voice Model in the train models tab.

    image

    ‎

  2. In Model name you name the model.

  3. Describe the model in Model Description.

  4. Select a Tag, such as English, Anime, etc.

  5. Upload an Image for the model, like the character's image.

  6. Upload the Model Zip containing the .PTH and .INDEX file.

  7. You're done!

# ‎
# ‎

# Uploading to Hugging Face

‎
‎

# 1. Zip the model

  • Select the correct .PTH & .INDEX & zip them into a .ZIP file.

  • Ensure it's .ZIP & not .RAR or .7ZIP.

# ‎

# 2. Log in

# ‎

# 3. Make repository

  1. Once logged in, tap your profile on the upper right corner, & then New Model.

    image

    ‎

  2. In Model name you name the repo as you want.

  3. Make sure License is set as openrail & the repo is set as Public.

  4. Once done, hit Create model.

    image ‎

# ‎

# 4. Upload model

  1. It will redirect you to the repo.
    Go to the Files and versions tab on the center, click + Add file on the right & then Upload files.

    image‎
    ‎

  2. Tap the upload box & submit the ZIP. Or just drag & drop.

    image‎
    ‎

  3. Tap on Commit changes to main & the model will begin to upload.

# ‎

# 5. Copy link (optional)

  • Once it's done, it will redirect you to the files list.

  • So if you need its link, right-click the download button ( ) of the .ZIP file on the right, and click Copy Link.

    image
# ‎

# You have reached the end.

Report Issues

© Copyright 2025. All rights reserved.