transcription
GitHub指导 Agent 处理 ChatCut 音视频转录任务。涵盖资产识别、导入、触发与监控转录进度、查找字幕及处理无音频等边界情况，并规范重试与修复逻辑，确保转录流程稳定执行。
Trigger Scenarios
Install
npx skills add ChatCut-Inc/agent-plugin --skill transcription -g -y
SKILL.md
Frontmatter
{
"name": "transcription",
"description": "Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin\/web surface — desktop sessions otherwise ship their own instructions and tools. Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup."
}
Transcription
- Use
browse_assetsto identify the video/audio asset and its transcription state. - For newly imported local media, complete the
asset-importworkflow first. - Check
track_progresswith targettranscription. It returns current status; follow the returned check-back guidance and do not busy-loop. - Use
find_transcriptfor timestamped text lookup. - 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.
Version History
-
014586d
Current 2026-08-27 10:44
优化了转录状态判断逻辑：明确 idle/error 状态下调用 trigger_transcript 的幂等性，区分进行中的任务与需重试的任务，并补充了通过 Web/Desktop 编辑器准备上传音频的流程。
-
926f56b
2026-08-12 11:07
移除对显式失败状态的立即重试逻辑，改为直接处理；新增无音频/无声被视为成功终态的处理规则。
-
e1867a8
2026-08-02 23:37
简化了流程步骤描述，明确了非终端状态下的等待策略（基于资产时长计算），新增了针对真实卡住或失败时的重试与修复操作指引，并强调了语义编辑与机械清理的区别。
-
f39cdae
2026-07-30 21:54
将获取资产ID和状态的方法从 read_project 改为 browse_assets；更新了本地资产不可达时的处理逻辑，明确通过 asset-import skill 重新上传而非 download_media；优化了卡住转录的重试判定逻辑示例。
- 5e9afe0 2026-07-22 10:58
