TUI app- Give it a YouTube URL (or a path to a video or audio file) and you get a transcription with possible speaker identification (WIP) and optional summary or translation, all thanks to open-source AI tooling and my lack of enough free time to watch content-sparse YouTube videos
features
transcribe YouTube videos by URL
transcribe YouTube videos by URL output metadata about the video
output metadata about the video speaker identification (probably using an LLM in conjunction with a speaker diarization library)
speaker identification (probably using an LLM in conjunction with a speaker diarization library) summarization via summarize (requires OPENAI_API_KEY to be set)
summarization via (requires to be set) translation via translate
translation via (requires to be set) can use almost any audio or video format that ffmpeg can handle as input, not just YouTube URLs
can use almost any audio or video format that can handle as input, not just YouTube URLs Test suite (run it with yt-transcriber TEST or TEST=1 yt-transcriber )
Test suite (run it with or ) support for other video platforms
... continue reading