Training AI Voice Models
Creating AI Voices
Start training custom AI voice models with Revocalize.
Prerequisite You should have your Revocalize account set up after going through
onboarding.
Setup your training data
Learn how to structure your training data to get the best results.Upload your audio training files
Upload your audio training files
- Create a folder in your repo called
audio. - Add dry acapella voice files to the
audiofolder. - Create the
model.jsonfile in the root of your repo. This file will contain the configuration for your model. The following is an example of amodel.jsonfile:
- Zip the
audiofolder andmodel.jsonfile together. - Upload the zip file through the Revocalize dashboard.
Record your training audio through Revocalize
Record your training audio through Revocalize
Revocalize allows you to record your training audio directly through the dashboard. This is a great option if you don’t have any audio files to train with.Simply head to the Revocalize dashboard and click the “Record Audio” button. You will be prompted to record your audio.
Once you are done, you can download the audio files and the
model.json file will be automatically generated for you.Optimize your training data
Optimizing your training data will help you get the best results from your custom voice model. We recommend the following guidelines when preparing your training data files:- Use dry acapella voice files - This means that the audio files should not contain any background music or sound effects (e.g. reverb, delay, etc.).
- Use high quality audio files - The audio files should be recorded in a quiet environment with minimal background noise (e.g. no traffic, no wind, etc.). Ideally the audio files should be recorded in a professional studio.
- Use a consistent volume level - The volume level of the audio files should be consistent across all files (e.g. no clipping, no distortion, etc.).
- Use a consistent sample rate - The sample rate of the audio files should be consistent across all files (e.g. 44.1kHz, 48kHz, etc.).
- Use a consistent bit depth - The bit depth of the audio files should be consistent across all files (e.g. 16-bit, 24-bit, etc.).
- Use a consistent file format - The file format of the audio files should be consistent across all files (e.g. WAV, AIFF, etc.).