this post was submitted on 11 Oct 2025
5 points (100.0% liked)

Opensource

4734 readers
97 users here now

A community for discussion about open source software! Ask questions, share knowledge, share news, or post interesting stuff related to it!

CreditsIcon base by Lorc under CC BY 3.0 with modifications to add a gradient



founded 2 years ago
MODERATORS
 

Using a open-weight model

The Shotcut 25.10 beta introduces text-to-speech support for the program's notes and subtitles functionality. Shotcut is making use of KokoroDoki for real-time text-to-speech support, which in turn is powered by the Kokoro 82M open-weight TTS model. KokoroDoki can leverage either CPUs or NVIDIA GPUs with CUDA for faster processing. KokoroDoki works with multiple languages and voices while all contained to the local device. The (American) English language support includes upwards of 20 different voices, eight for British English, and less coverage for other languages.

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here