Agent Skills0xsline/OpenChatCut › transcription

transcription

GitHub

处理音视频转写、字幕生成与样式设置。涵盖转录进度跟踪、文本搜索、本地媒体导入及异常重试逻辑,确保ASR就绪并管理字幕状态。

src/agent/skills/transcription/SKILL.md 0xsline/OpenChatCut

Trigger Scenarios

需要为视频或音频添加字幕或转写文本 检查转录进度或重试失败的转写任务 搜索转录内容或启用/编辑字幕

Install

npx skills add 0xsline/OpenChatCut --skill transcription -g -y
More Options

Non-standard path

npx skills add https://github.com/0xsline/OpenChatCut/tree/main/src/agent/skills/transcription -g -y

Use without installing

npx skills use 0xsline/OpenChatCut@transcription

指定 Agent (Claude Code)

npx skills add 0xsline/OpenChatCut --skill transcription -a claude-code -g -y

安装 repo 全部 skill

npx skills add 0xsline/OpenChatCut --all -g -y

预览 repo 内 skill

npx skills add 0xsline/OpenChatCut --list

SKILL.md

Frontmatter
{
    "name": "transcription",
    "description": "Use when a video\/audio task needs OpenChatCut transcription, captions, subtitles, subtitle styling, transcript search, transcript readiness checks, or enabling captions, including local or attached videos where the user asks to add captions\/subtitles, transcribe, create bilingual subtitles, clean talking-head speech, remove filler words, or trim pauses."
}

Transcription

For newly imported local/client-held media, use import_media to start transcription, then wait with track_progress.

Typical flow:

  1. read_project with view: "assets" to get the video/audio asset ID and transcript status.
  2. If this is a fresh client-held import, make sure it went through import_media action=create_session plus the OpenChatCut media import helper.
  3. Call track_progress with action:"wait", target:"transcription", and assetIds set to the asset ID or prefix.
  4. Use find_transcript to search transcript text and confirm word timestamps.
  5. Use edit_captions action enable or read_captions as needed once transcription is ready.

Example:

{
  "action": "wait",
  "target": "transcription",
  "assetIds": "13c1aa02cd"
}

Uploaded assets start ASR automatically on ingest, but nothing waits for it. Always use track_progress for readiness.

For local-only video assets with local-only; original upload deferred in read_project, transcription cannot run until the bytes are reachable by the backend. Import the source again via the asset-import skill (which uploads to S3) or download_media from a public URL; do not ask the user to relink it manually in the editor.

Stuck Transcription And Retry

Do not declare transcription stuck from one non-terminal status. Base the decision on both asset length and the time the agent has actually waited in this task.

  1. Read the asset with read_project view: "assets" and note its duration when available.
  2. Start counting elapsed wait time from the first track_progress action:"wait" or from the earliest reliable in-task timestamp where the agent observed transcription as pending/running.
  3. If transcription reports an explicit failed, errored, or timed-out terminal state, retry immediately after confirming the asset is remote-ready and is video/audio.
  4. If transcription remains pending/running with no failure, treat it as stuck only after elapsed wait time exceeds max(5 minutes, min(60 minutes, 2 × asset duration)). For example, wait at least 5 minutes for a 30-second clip, about 20 minutes for a 10-minute asset, and about 60 minutes for a 1-hour or longer asset.
  5. If duration is unknown, wait at least 10 minutes across more than one track_progress call before treating it as stuck, unless the tool reports an explicit failure.

When stuck, use manage_transcript with action: "retry_transcription" and the asset id/prefix. This force-retries ASR for audio/video assets and starts a new transcription run; it does not wait for completion. After retrying, call track_progress with target:"transcription", action:"wait", and the returned or same asset id before reading transcripts or captions.

Example retry:

{
  "action": "retry_transcription",
  "asset": "13c1aa02cd"
}

If captions read back as empty, check the source-time range of the timeline clip. A transcript can be ready while the current visible clip starts before the first spoken word; add or trim a clip so the transcribed source words fall inside the timeline range, then extend/update the captions item duration if needed.

Use the raw tools when you need finer control:

  • track_progress with target: "transcription" for status/wait.
  • find_transcript for query-based transcript lookup.
  • read_captions and edit_captions for caption display edits.
  • manage_transcript action fix for source transcript repair.
  • manage_transcript action retry_transcription to force-retry ASR after a transcription is stuck, timed out, or failed.
  • clean_script for mechanical timeline playback cleanup of fixed fillers and batch pauses after transcript-ready media is on the timeline.

When a transcript-ready request becomes an editorial talking-head edit, follow the public-safe talking-head workflow in shared talking-head-guide. In short: use clean_script only for mechanical cleanup, then use Script (read_script -> edit timeline.md -> apply_script) for semantic repeated-take, silence, filler, or coherence edits, and verify the resulting script rather than trusting tool success alone.

Version History

  • 0c0c02d Current 2026-08-12 09:08

Same Skill Collection

src/agent/skills/ai-cinematic-short-film/SKILL.md
src/agent/skills/asset-import/SKILL.md
src/agent/skills/create-motion-graphics/SKILL.md
src/agent/skills/explainer-video/SKILL.md
src/agent/skills/export/SKILL.md
src/agent/skills/image-gen/SKILL.md
src/agent/skills/known-errors/SKILL.md
src/agent/skills/long-video-to-shorts/SKILL.md
src/agent/skills/motion-graphic-placement/SKILL.md
src/agent/skills/multi-clips-to-reels/SKILL.md
src/agent/skills/music-intelligence/SKILL.md
src/agent/skills/music/SKILL.md
src/agent/skills/news-rough-cut/SKILL.md
src/agent/skills/openchatcut-plugin-basics/SKILL.md
src/agent/skills/product-ad-video-script/SKILL.md
src/agent/skills/shader-gen/SKILL.md
src/agent/skills/storyboard-shot-breakdown/SKILL.md
src/agent/skills/verification/SKILL.md
src/agent/skills/video-gen/SKILL.md
src/agent/skills/video-thumbnail-generator/SKILL.md
src/agent/skills/voice/SKILL.md
src/agent/skills/widget-forms/SKILL.md
skills/openchatcut/SKILL.md
src/agent/skills/product-help/SKILL.md
src/agent/skills/talking-head-guide/SKILL.md

Metadata

Files
0
Version
f56fc2f
Hash
4a47ef20
Indexed
2026-08-12 09:08

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-13 04:41
浙ICP备14020137号-1 $お客様$