Transcribe Vaam Video with Gemini

Documents

Transcribe Vaam Video with Gemini is an Agent Skill for documents published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Transcribe Vaam videos using Google Gemini AI. Takes a Vaam share URL, downloads the video, and returns a full text transcription. Supports any language without translation.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/transcribe-vaam-video-with-gemini/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/transcribe-vaam-video-with-gemini, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

IMPORTANT - Path Resolution: This skill can be installed in different locations. Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below. Replace $SKILL_DIR with the actual discovered path.

Transcribe Vaam Video with Gemini

Transcribe Vaam video recordings using Google Gemini AI. Provide a Vaam share URL and get back a complete text transcription.

Setup (First Time Only)

cd $SKILL_DIR && bun install

This installs the required dependencies (Google Generative AI SDK).

Requirements

Environment Variable:

GEMINI_API_KEY - Required. Your Google Gemini API key.
- Get one at: https://aistudio.google.com/apikey

Usage

cd $SKILL_DIR && bun lib/transcribe-with-gemini.ts <vaam-url>

Options

Option	Description
`--help`, `-h`	Show help message
`--verbose`, `-v`	Enable progress logging (only use for debugging)

Examples

# Basic transcription
cd $SKILL_DIR && bun lib/transcribe-with-gemini.ts https://app.vaam.io/share/abc123

# With verbose output (shows progress)
cd $SKILL_DIR && bun lib/transcribe-with-gemini.ts --verbose https://app.vaam.io/share/abc123

Input

Vaam Share URL: Must be in format https://app.vaam.io/share/[id]
- The ID can contain letters, numbers, and hyphens

Output

On Success:

Plain text transcription to stdout
Exit code: 0

On Error:

JSON error object to stdout with structure:

{
  "success": false,
  "error": {
    "code": "ERROR_CODE",
    "message": "Human-readable message",
    "details": "Technical details",
    "suggestion": "How to fix it"
  }
}

Exit code: 1 (validation errors) or 2 (runtime errors)

Error Codes

Code	Description	Exit Code
`MISSING_ARGUMENT`	No URL provided	1
`INVALID_URL`	URL doesn't match expected format	1
`MISSING_API_KEY`	GEMINI_API_KEY not set	1
`VIDEO_EXTRACTION_FAILED`	Couldn't get video from Vaam	2
`VIDEO_DOWNLOAD_FAILED`	Couldn't download video file	2
`TRANSCRIPTION_FAILED`	Gemini API error	2

How It Works

Parses the Vaam share URL to extract the capture ID
Fetches the video URL from Vaam's API
Downloads the video to a temporary file
Sends the video to Gemini for transcription
Returns the transcription text
Cleans up temporary files

Notes

Videos are transcribed in their original language (no automatic translation)
Includes spoken content and important visual information shown on screen
Timestamps are not included in the transcription
Temporary files are automatically cleaned up after processing
Gemini supports videos up to 2GB