Follow this doc for Open Voice Setup: https://github.com/Alienpups/OpenVoice/blob/main/docs/USAGE_WINDOWS.md Apart from this, install ffmpeg for windows https://www.ffmpeg.org/download.html#build-windows Add ffmpeg binaries to your path variable. Restart laptop for changes to get reflected on VSCode.

Follow whisper doc for speech to text. https://github.com/openai/whisper/blob/main/README.md Use this code and run the python script. Also, replace the audio files as per your requirement. The audio files 'Sample2.m4a' and 'demo_bka_speaker.mp3' were my own audios for testing purposes. Please create your own sample audios and replace them.