transcribe
starsforks
How to install transcribe?
comol/ai_rules_1c/transcribe
$npx -y skills add comol/ai_rules_1c --skill transcribeTranscribe 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.
SKILL.md
| 1 | # transcribe — video and audio transcription |
| 2 | |
| 3 | Transcribes audio and video files via the Gemini 2.5 Flash API. |
| 4 | |
| 5 | ## Modes |
| 6 | |
| 7 | ### Generic (default) |
| 8 | Verbatim speech transcription with timecodes `[MM:SS]` and speaker identification. |
| 9 | |
| 10 | Output files: |
| 11 | - `<name> - transcript.md` — verbatim speech with timecodes |
| 12 | - `<name> - summary.md` — short summary (with the `--with-summary` flag) |
| 13 | |
| 14 | ### UI analysis (`--analyze-ui`, video only) |
| 15 | Detailed video analysis with breakdown of on-screen interface, navigation, and actions, plus screenshots. |
| 16 | |
| 17 | Output files: |
| 18 | - `<name> - summary.md` — short overview (topic, participants, decisions) |
| 19 | - `<name> - detailed.md` — step-by-step chronological analysis with screen content and screenshots |
| 20 | - `<name> - transcript.md` — verbatim speech with timecodes |
| 21 | - `screenshots/` — PNG frames of key moments |
| 22 | |
| 23 | ## Usage |
| 24 | |
| 25 | ``` |
| 26 | /transcribe <FilePath> [--output-dir DIR] [--analyze-ui] [--with-summary] [--format md|txt] |
| 27 | ``` |
| 28 | |
| 29 | | Parameter | Required | Default | Description | |
| 30 | |-----------|:--------:|---------|-------------| |
| 31 | | `FilePath` | yes | — | Path to audio / video file | |
| 32 | | `--output-dir` | no | `<file_folder>/Transcript/<name>/` | Result directory | |
| 33 | | `--analyze-ui` | no | off | UI-analysis mode (video only) | |
| 34 | | `--with-summary` | no | off | Add a summary (for generic mode) | |
| 35 | | `--format` | no | `md` | Output format: `md` or `txt` | |
| 36 | |
| 37 | ## Supported formats |
| 38 | |
| 39 | - **Video:** mp4, mkv, webm, avi, mov |
| 40 | - **Audio:** mp3, wav, ogg, m4a, flac, aac, wma |
| 41 | |
| 42 | ## Dependencies |
| 43 | |
| 44 | - Python packages: `google-genai`, `python-dotenv` |
| 45 | - System: `ffmpeg`, `ffprobe` in PATH |
| 46 | - API key: environment variable `GEMINI_API_KEY`, or `<skill-dir>/.env` with `GEMINI_API_KEY=...` (the script also checks supported user-skill locations and then `cwd/.env`) |
| 47 | |
| 48 | ## Procedure |
| 49 | |
| 50 | 1. Determine `FilePath` and optional flags from the user's arguments. |
| 51 | |
| 52 | 2. Run the script: |
| 53 | |
| 54 | ```powershell |
| 55 | $env:PYTHONUNBUFFERED = "1" |
| 56 | python <skill-dir>/scripts/transcribe.py "<FilePath>" [--output-dir "<OutputDir>"] [--analyze-ui] [--with-summary] [--format md|txt] |
| 57 | ``` |
| 58 | |
| 59 | **IMPORTANT:** `PYTHONUNBUFFERED=1` is mandatory; otherwise stdout is buffered and progress is not displayed. |
| 60 | |
| 61 | On macOS / Linux use `PYTHONUNBUFFERED=1 python ...` instead. |
| 62 | |
| 63 | 3. The script runs long (5–15 minutes depending on length). Files > 1 hour are split automatically. |
| 64 | |
| 65 | 4. After completion, report the result paths to the user. |
| 66 | |
| 67 | 5. Read the summary (if any) or the start of the transcript and show it to the user. |
| 68 | |
| 69 | ## Cost |
| 70 | |
| 71 | ~$0.10 per 1 hour of recording (Gemini 2.5 Flash). Long files cost proportionally. |
| 72 | |
| 73 | ## Limitations |
| 74 | |
| 75 | - Maximum ~1 hour per Gemini request (the script splits automatically) |
| 76 | - Cyrillic file names: the script automatically copies the file to a temp location with an ASCII name |
| 77 | - Screenshot quality depends on source video quality |
| 78 | - Timecode accuracy +/- a few seconds |
| 79 | - `--analyze-ui` with an audio file automatically falls back to generic + summary |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
