菜单
Transcribe video and audio files via Gemini API. Use when the user asks to transcribe a recording, generate a meeting summary, extract speech from video or audio, or convert speech to text. Supports mp4, mkv, webm, avi, mov, mp3, wav, ogg, m4a, flac.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
1C metadata management — create, edit, validate, and remove configuration objects (catalogs, documents, registers, enums), managed forms, data composition schemas (SKD), spreadsheet layouts (MXL), roles, external processors (EPF/ERF), extensions (CFE), configurations (CF), databases, subsystems, command interfaces, templates. Use when working with 1C metadata structure.
Catalog of MCP servers for 1C development — search, code navigation, metadata, code review, docs, ITS, templates. Use whenever a 1C task requires calling tools from any 1c-*-mcp / 1C-*-mcp server. Each server has its own detail file under `docs/` — load it when you are about to call tools from that server, and only if the server is actually available in the current session.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
| name | transcribe |
| description | Transcribe video and audio files via Gemini API. Use when the user asks to transcribe a recording, generate a meeting summary, extract speech from video or audio, or convert speech to text. Supports mp4, mkv, webm, avi, mov, mp3, wav, ogg, m4a, flac. |
Transcribes audio and video files via the Gemini 2.5 Flash API.
Verbatim speech transcription with timecodes [MM:SS] and speaker identification.
Output files:
<name> - transcript.md — verbatim speech with timecodes<name> - summary.md — short summary (with the --with-summary flag)--analyze-ui, video only)Detailed video analysis with breakdown of on-screen interface, navigation, and actions, plus screenshots.
Output files:
<name> - summary.md — short overview (topic, participants, decisions)<name> - detailed.md — step-by-step chronological analysis with screen content and screenshots<name> - transcript.md — verbatim speech with timecodesscreenshots/ — PNG frames of key moments/transcribe <FilePath> [--output-dir DIR] [--analyze-ui] [--with-summary] [--format md|txt]
| Parameter | Required | Default | Description |
|---|---|---|---|
FilePath | yes | — | Path to audio / video file |
--output-dir | no | <file_folder>/Transcript/<name>/ | Result directory |
--analyze-ui | no | off | UI-analysis mode (video only) |
--with-summary | no | off | Add a summary (for generic mode) |
--format | no | md | Output format: md or txt |
google-genai, python-dotenvffmpeg, ffprobe in PATH~/.cursor/skills/transcribe/.env (or your tool's skill folder) with GEMINI_API_KEY=...Determine FilePath and optional flags from the user's arguments.
Run the script:
PYTHONUNBUFFERED=1 python <skill-dir>/scripts/transcribe.py "<FilePath>" [--output-dir "<OutputDir>"] [--analyze-ui] [--with-summary] [--format md|txt]
IMPORTANT: PYTHONUNBUFFERED=1 is mandatory; otherwise stdout is buffered and progress is not displayed.
The script runs long (5–15 minutes depending on length). Files > 1 hour are split automatically.
After completion, report the result paths to the user.
Read the summary (if any) or the start of the transcript and show it to the user.
~$0.10 per 1 hour of recording (Gemini 2.5 Flash). Long files cost proportionally.
--analyze-ui with an audio file automatically falls back to generic + summary