mcpField
T
transcription

transcription

github.com/chatcut-incCreative & media988149 installsUpdated today
Repository

About transcription

transcription is a ChatCut skill for managing media transcription and caption workflows. It guides agents through asset checks, progress monitoring, timestamped transcript lookup, and recovery of failed or stalled jobs.

Key features

  1. 01Check media assets and transcription state
  2. 02Monitor transcription progress
  3. 03Find timestamped transcript text
  4. 04Enable, inspect, translate, or style captions
  5. 05Retry failed or stalled transcription

Use cases

  1. 01Check whether an imported clip has a transcript
  2. 02Find speech at a particular timestamp
  3. 03Prepare or translate captions after transcription
  4. 04Recover an explicitly failed transcription

MCP support

The skill directs agents to use ChatCut tools such as browse_assets, track_progress, find_transcript, and trigger_transcript. It describes tool workflows rather than providing an MCP server.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/chatcut-inc/agent-plugin --skill transcription

After installing, type/transcriptionin Claude Code to confirm it loaded.

Details

From the project README

Transcription

  1. Use browse_assets to identify the video/audio asset and its transcription state.
  2. For newly imported local media, complete the asset-import workflow first.
  3. Check track_progress with target transcription. It returns current status; follow the returned check-back guidance and do not busy-loop.
  4. Use find_transcript for timestamped text lookup.
  5. Use the current caption tools to enable, inspect, translate, or style captions only after transcription is ready.

Do not call a transcription stuck from one pending status. Treat an explicit failed terminal state immediately; otherwise allow at least max(5 minutes, min(60 minutes, 2 x asset duration)), or at least 10 minutes across multiple checks when duration is unknown.

no_audio / no-speech is a successful terminal analysis result: the media is usable, but there is no transcript to read or caption. Do not report it as a transcription failure or retry it unless the user says the media contains speech that should have been detected.

Use trigger_transcript when the user explicitly wants transcription started or restarted. It is idempotent: only idle and error start work; ready, no-audio, and in-progress assets are left unchanged. If prepared transcription audio exists it is reused; otherwise the open Web/Desktop editor is asked to prepare and upload audio through its native pipeline. Then inspect readiness with track_progress.

For an idle or explicitly failed (error) run, call trigger_transcript with the asset id, then check transcription progress again. If an in-progress run has genuinely exceeded the stuck threshold, use manage_transcript action retry_transcription because trigger_transcript intentionally leaves in-progress work unchanged. The manage tool also remains available for low-level recovery where an external MCP host must supply prepared audioBase64. Repair source words with the transcript-fix action instead of rewriting visible captions when the source transcript itself is wrong.

For semantic speech edits, load talking-head-guide and use the Script workflow. Use mechanical cleanup only for fixed fillers and pauses; do not replace transcript-aware editing with destructive physical timeline cuts.

Comments

Markdown supported