Experimentation with voice cloning for performance.
Project description
voice-puppet
Command line tool to clone voice with TTS. Can be used for individual lines or fed a script file.
Basic usage:
voice_puppet --clone AUDIOFILETOCLONE.wav --text "Text to say." --output "cloned.wav"
Usage with a script file
You can also provide a script file and a folder with voices to clone.
voice_puppet --script SCRIPTFILE.txt --voices FOLDERWITHVOICES --output OUTPUTDIRECTORY
The script file should follow this format:
## Scene 1
### Karl
A spectre is haunting this script.
### Fred
The spectre of voice cloning.
## Scene 2
### Karl: excited
So many spectres!
A folder will be created for each scene, and indidual wav files for each line of dialog.
Scene names are preceded by 2 hashes ##
.
Lines of dialog are preceded by 3 hashes ###
, followed by a voice file to use as the source of the clone, and optionally followed by a colon and a mood.
You must provide a folder with wav files for each voice that matches the names you put in the script. So if you write "Karl" in the script, there should be a file called Karl.wav
in a voices
directory (or another directory name that you can specify).
If you optionally provide a mood with a character name, you should provide another voice file, in the format Character_mood.wav
.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for voice_puppet-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 50c82567985fd302c8298a2adb1be6a37ade1d406b4858a1f2343e4d264a382c |
|
MD5 | 614abbda4f5a25003e95639fbaaa7f88 |
|
BLAKE2b-256 | 2e616b39730b435de53eaae8b2cad5ef160360b038dfb12cea374b7d6d9cdcd4 |