text-generation: gpt4all 13b snoozy https://gpt4all.io/reports/GPT4All_Technical_Report_3.pdf

text-to-speach: silero-tts  https://github.com/GhostNaN/silero-webui

frontend: oobabooga text-generation-webui https://github.com/oobabooga/text-generation-webui

musik: musicGen https://huggingface.co/facebook/musicgen-melody

sound editing: ardour https://github.com/Ardour

video editing: kdenlive https://github.com/KDE/kdenlive

prompting: christian asbach und blafasel

editing: christian asbach