Repository navigation
Run the video skills on Node, with nothing to install - #28
Merged
Merged
Conversation
record.py, polish.py and voiceover.py needed Python 3, uv, Pillow and websockets. The ports use Node 22's WebSocket and fetch; polish lays out each frame in a headless Chrome through agent-browser instead of drawing with Pillow. Kokoro keeps its Python runner, since the model is Python-only.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
record-demoandadd-voiceoverwere the only skills that needed Python: Python 3,uv, Pillow and websockets. Anyone recording a demo already has Node, since agent-browser installs from npm. Now both skills run on Node 22 or later with nothing to install.record.mjsandvoiceover.mjsare straight ports. Node 22's built-inWebSocketandfetchreplace websockets and urllib.polish.mjslays out each frame as a web page (polish.html) in a headless Chrome through agent-browser, and pipes screenshots to ffmpeg. Chrome draws the card, window chrome, pointer and rings, which replaces about 150 lines of Pillow drawing.Polish takes about 6 s per second of video: 4 min 54 s for a 50 s take on a busy machine.
Checked against the Python version on the 50 s demo from #26:
voiceover.mjswrites an identicallines.jsonand reuses every cached line (cache keys match, including non-ASCII text).record.mjslogs the same beats, pointer moves and clicks, and the opening scroll gets a new frame on all but 3 of about 120 frames.--frame safariand--background nonewere each rendered on a 3 s clip.Stacked on #26.
Created with Claude Opus 5.5 in Claude Code.