🎬➜📄 DocuMaker
Turn a tutorial video into a step-by-step DOCX guide with screenshots. Transcription runs locally (Whisper); the guide text uses a free HuggingFace model via your token; image captions use local BLIP.
Create a token at huggingface.co/settings/tokens (a free Read token works). It's kept in memory for this session only.
1 · Upload & preview
2 · Transcribe → 3 · Generate guide
4 · Capture & extract frames
Auto-extract uses the transcript + step outline (steps 2–3) to pull frames at the guide's step moments and skip recorder intro/idle screens — it will run those first if needed. Capture current frame grabs the exact moment showing in the player above.