Bug 478654

Summary: [Feature Request] Implement Text-To-Speech (TTS)
Product: [Applications] kdenlive Reporter: Balr Gend <balrogwhip123123>
Component: Video Effects & TransitionsAssignee: Jean-Baptiste Mardelle <jb>
Status: REPORTED ---    
Severity: wishlist CC: berndmj
Priority: NOR    
Version: 23.04.2   
Target Milestone: ---   
Platform: Other   
OS: Other   
Latest Commit: Version Fixed In:
Sentry Crash Report:

Description Balr Gend 2023-12-17 17:18:33 UTC 
As title says, I want this future to be implemented. This will be very good for overall workflow and set of tools of kdenlive.
Implement TTS with any type of TTS engines and models (libre/free voice models from Espeak-ng must be considred first). 

Might be even AI voice cloning/transforming?

Similar functionality can be found in Capcut and Balabolka.

P.S. Sorry for bad bug ticket format, I wanted to make it quick and all at once since I am short on time.