Voice Cloning
In this section, you’ll learn how to clone your voice in EchoKit. The process has three main steps:
- Process your voice data to reate high-quality audio samples, which will take 60 minutes - 90 minutes, depending on the voice quality.
- Fine tune the GPT-SoVits model using the processed audio from Step 1, which will take 20 minutes
- Deploy the fine-tuned model, which will take 20 minutes.