search

Jiangshan00001 / pyttsx4

Offline Text To Speech synthesis for python
Mozilla Public License 2.0
43 stars 8 forks source link

Allow adding multiple voice samples for voice cloning #11

Closed Dgarc359 closed 1 year ago

Dgarc359 commented 1 year ago

Is your feature request related to a problem? Please describe. The example code shows how to provide a sample .wav file for vocal cloning. Is it possible / necessary to add more voice samples to improve accuracy of vocal cloning? Either that, or some guidelines on how to best produce a vocal clone with a single sample

Describe the solution you'd like

# when calling engine.setProperty() - allow multiple file paths to be passed
engine.setProperty('speaker_wav', ['./speaker_sample_1.wav', './speaker_sample_2.wav']
Jiangshan00001 commented 1 year ago

i think it is not needed. i added some example input and output of the wav file. see the repo readme.md extera features 2.