Released this evening is the first beta of the Shotcut 25.10 open-source video editor. This prominent video editing application for Linux systems is introducing yet more AI-powered functionality.
Since last year Shotcut has been seeing some AI features like integrating OpenAI’s Whisper for speech-to-text support. With Shotcut 25.10 they are baking the inverse in text-to-speech support.
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.
Making this text-to-speech support more complicated is that it relies on Docker for execution, among other factors.
Shotcut 25.10 beta also adds a “Text: Typewriter” video filter, “Image/Video from HTML” functionality via Chrome/Chromium, and is now making use of the FFmpeg 8.0 library and other updates. There are also many other fixes and improvements to be found with this forthcoming Shotcut 25.10 video editor update.
Shotcut 25.10 beta downloads and more information on this open-source video editor update via GitHub.
