A webapp for cloning voice based from this repo
- Install the dependencies found in
requirements.txt
- Download the pretrained models from here and save it to their respective directories
- Run
app.py
- Record or upload the voice you want to be cloned. The audio will be saved in
uploads
directory - Enter the script that you want the voice to speak
- Play or download the synthesized audio. Synthesized audio will be stored in
static/cloned/
directory
- uses
SoX
shell script to remove the silent part from the synthesized audio