Honestly, cutting video with just Claude Whisper sucks.
Audio (waveform) ๐ฅ word timestamp (transcript) alignment = not accurate.
We did tests and found that using Montreal Forced Aligner improves the accuracy for mistakes/retakes A LOT (cc
@happylinks). Even on first run.
Works best in English, Spanish, Italian, French, Mandarin, Portuguese.
Updated my Claude skill for vid cutting on Github๐
Lots of people asked how I used Fable to edit its own launch video so I made a video about that!
TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it.
I didn't touch a video editor.