BaoCut: Video Transcription and Editing Skill
tinyfool · x · 2026-07-16
This is a subtitle transcription, translation, and editing Skill called BaoCut, designed for Agent workflows.
Using a CLI, it allows Agents to perform video transcription, speaker identification, text refinement (fixing typos and filler words), translation, and basic editing based on the transcript (like removing filler words and repetitions). The author emphasizes that the main goal is to solve the lack of a user-friendly secondary editing interface after an Agent finishes transcription and translation.
Currently, the workflow is: the Skill provides a CLI, the Agent executes transcription and processing while syncing progress to a GUI in real-time, and users can then preview and manually edit within the GUI. Known limitations include Mac-only support and slower translation speeds, though the quality is higher.
Related event: BaoCut: Video Transcription and Rough Cut Skill for Agents(4 posts)→
More from coding & agent
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11