feat(studio): add full video editing pipeline with filler removal#698
Open
Adn19900 wants to merge 1 commit intoheygen-com:mainfrom
Open
feat(studio): add full video editing pipeline with filler removal#698Adn19900 wants to merge 1 commit intoheygen-com:mainfrom
Adn19900 wants to merge 1 commit intoheygen-com:mainfrom
Conversation
Adds a `studio/` directory with three files that together form a complete raw-video-to-motion-graphics pipeline: - `remove_fillers.py` — transcribes a video with Whisper, detects filler words (um, uh, like, you know, etc.), and uses FFmpeg to cut them out. Supports dry-run, custom filler lists, and all Whisper model sizes. - `pipeline.py` — end-to-end orchestrator that accepts either a raw video file (filler removal → HyperFrames project scaffold) or a plain-text script (TTS narration → transcribe → HyperFrames project scaffold). - `SETUP.md` — prerequisites guide (Node 22, Bun, FFmpeg, Whisper), pipeline usage examples, HyperFrames workflow commands, and a quick-reference table for Whisper models and TTS voices. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
studio/remove_fillers.py-- transcribes a video with Whisper and uses FFmpeg to cut out filler words (um, uh, like, you know, etc.). Supports dry-run, custom filler word lists, and all Whisper model sizes.studio/pipeline.py-- end-to-end orchestrator that accepts a raw video file (filler removal -> HyperFrames scaffold) or a plain-text script (TTS -> transcribe -> HyperFrames scaffold).studio/SETUP.md-- prerequisites guide (Node 22, Bun, FFmpeg, Whisper), pipeline usage examples, and quick-reference tables for Whisper models and TTS voices.Test plan
python studio/remove_fillers.py sample.mp4 --dry-runprints detected filler segments without writing a filepython studio/remove_fillers.py sample.mp4 out.mp4produces a video shorter than the inputpython studio/pipeline.py sample.mp4 --project test-projscaffolds a HyperFrames project withtranscript.jsonpython studio/pipeline.py script.txt --project test-projruns TTS -> transcribe -> scaffoldGenerated with Claude Code