DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to cut dead air and keep existing captions in sync with Open Edit

Find speech ranges, apply a cut list in one encode, and retime the transcript to match.

  • Content
  • Advanced
  • 60 minutes
  • From the README
  • Claude Code
  • Codex
  • Gemini CLI

Who it is forA podcaster or editor with a talking video that has long pauses and an existing transcript.

The problemCutting a video after captioning breaks the word timings unless they are moved to match.

The outcomeA cut MP4 with crossfaded joins and a retimed transcript that matches the cut without transcribing again.

What you need first

  • Node.js, so that npx can run @veedstudio/openedit-cli
  • A workspace folder for the project
  • FFmpeg, which install-ffmpeg can find or download
  • A VEED login for hosted transcription and the VEED editor handoff
  • A fal key (FAL_KEY) only for fal-billed models, background removal with --fal or --fast, and lipsync

Steps

  1. Run npx @veedstudio/openedit-cli speech-probe --gap 250 --json to measure where speech starts, stops, and pauses. (inferred, check the README)
  2. Write the kept ranges into an edl.json file, using seconds for the ranges.
  3. Run npx @veedstudio/openedit-cli apply-edl --edl edl.json --out cut.mp4 --crossfade 40 to build the cut. (inferred, check the README)
  4. Run npx @veedstudio/openedit-cli retime-transcript --edl edl.json --out runs/cut/transcript.json to move the timings onto the cut. (inferred, check the README)

Prompt for your agent

In the veedstudio/open-edit repo, probe speech in <video path>, write an edl.json with the kept ranges, then run apply-edl and retime-transcript. Expect cut.mp4 and a retimed transcript under runs/cut. Verify that the retimed transcript timings fall inside the cut duration.

Caveat. The README says the EDL is in seconds while --gap and --crossfade are in milliseconds, so check units before you run it.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page