VoiceCraft is a text to speech (TTS) and speech editing project written by Puyuan Peng which provides some interesting results for voice cloning with just a few seconds of input data. If you’re looking to try this tool out yourself but have hit some hurdles, I’ve created this guide which walks you through its use on Windows using Docker. You should have a little familiarity with Python to be able to use this tool.
Continue reading
If you’ve had trouble using LyCORIS in automatic1111 Stable Diffusion web UI chances are you’re using the Docker version. To get it to work, you’ll need to make a small change – but I’ll quickly lay out how to get it up and running in your container from start to finish.
Continue readingCorentin Jemine (CorentinJ on GitHub) has a project called Real Time Voice Cloning available on GitHub that uses deep learning to take a voice as input and synthesize speech using its properties – in essence creating a “deep fake” of audio. Setting things up from scratch to get it working on Windows 10 involves using specific versions of software and can be a bit difficult for new users to figure out. I intend this as a reference guide for doing just that – assuming you are starting with a fresh Windows 10 install. This does not provide any instruction for using the cloning software once setup.
Continue reading