Hi,

We want a Google collab notebook, to perform deepfake audio generation

There are many resources available online, e.g. https://github.com/CorentinJ/Real-Time-Voice-Cloning

We need a notebook designed as follows:

Input parameters (to be set at the top of the notebook):
- Link to a sample of the target speaker’s voice (open to any format you propose: .wav, etc)
- Text to be spoken, in the target speaker’s voice (e.g. “Hi, this is the generated audio by the target speaker!”)

Output:
- Audio file of the the target speaker saying the requested text (again, open to any format you propose)

Budget: $25
Posted On: March 16, 2023 08:41 UTC
Category: Deep Learning
Skills:Python
Country: United States
click to apply