Menu

Individual skill

gtrk-transcript

将用户本地视频或音频（自备配音）转成一个飞书妙记式 Markdown 文字稿，并由 Agent 基于完整转写生成总结；音频配 --json 时另产句级时码 transcript.json（音频驱动工程兜底路输入）。用户说“视频转文字稿 / 视频转文字 / 提取视频文稿 / 把本地视频整理成文字稿或妙记 / 给我自己录的配音出时码稿”时使用。只处理本地文件，不接受 URL、平台链接或远端下载。

skills/gtrk-transcript/SKILL.md

Read pinned source

Source commit 6d888abd6f5b7e01046e54b8572dd3342c366c39

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
963
Repository last updated
Oct 30, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# gtrk 视频/音频转文字稿

飞书使用教程统一入口：[gtrk CLI 使用教程](https://hocassian.feishu.cn/wiki/HCFpwoF7SivIFbkKosgcFMcEnxk)。

本 Skill 驱动一级命令 `gtrk transcript`，最终只交付一个 Markdown：总结、带 `[00:01:23]` 时间戳的可读文字记录、完整纯文本。

## 音频输入与 transcript.json（自备配音时码化兜底）

- 输入白名单已放开音频：wav/mp3/flac/m4a/aac/ogg 等本地音频文件可直接转写（音频无「抽音频」步——已是音频，仍本地转 16k 单声道后只传转码衍生物，原文件不动）。
- `--json` 除机读 stdout 外**另产 `<名>-transcript.json`**（`utterances[]{id,text,st,ed}` + `material_id` + `text_hash` + `duration`，结构与 `gtrk split` 消费契约逐字段对齐）；结果 JSON 的 `transcriptJson` 字段给出路径，可直接被 `gtrk project init --audio <配音> --transcript <该文件>` 兜底路消费。
- **定位注记（MUST 遵守）：TTS 主路勿走本零件**——`gtrk tool audio_tts_clone` 产的配音自带句级 segments（时码直出、零成本零误差），建工程直接 `gtrk project init --tts-task <task_id>`；对 TTS 产物再跑一遍 ASR 转写=重复计费零收益。本零件只服务**自备配音**（用户自录旁白等无时码音频）场景。

## 硬边界