yapsnap
Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.
yapsnap " https://www.youtube.com/watch?v=dQw4w9WgXcQ "
That's it. You get a .txt next to your shell, transcribed on your CPU, in less time than it took the video to play.
Why yapsnap
β‘ Fast on CPU. Streaming Zipformer transducer (Kroko English) chews through audio at several times realtime on a laptop. No CUDA. No M-series-only tricks. Plain old cores.
Streaming Zipformer transducer (Kroko English) chews through audio at several times realtime on a laptop. No CUDA. No M-series-only tricks. Plain old cores. π Any video URL, plus local files. YouTube. X. TikTok. Instagram Reels. Direct .mp4 / .mp3 links. Or just point it at a file on disk. yt-dlp handles the fetch, ffmpeg handles the decode, the rest is yours.
YouTube. X. TikTok. Instagram Reels. Direct / links. Or just point it at a file on disk. yt-dlp handles the fetch, ffmpeg handles the decode, the rest is yours. π΄ Offline after first run. ~80 MB model downloads once to your cache and stays there. No API keys. No quotas. Your audio never leaves your machine.
~80 MB model downloads once to your cache and stays there. No API keys. No quotas. Your audio never leaves your machine. πͺΆ One file, three deps. sherpa-onnx , numpy , yt-dlp . The whole tool is a single Python module.
, , . The whole tool is a single Python module. β± Sentence-level timestamps when you want them. --timestamps adds [MM:SS] per sentence using Kroko's built-in punctuation. Timing stays correct even when you transcribe at 2x.
... continue reading