mcpField
T
transcribe

transcribe

github.com/aviz85Creative & media5039 installsUpdated 16w ago
Repository

About transcribe

A command-line skill that creates SRT subtitles from audio or video using ElevenLabs Scribe v2. It supports automatic or specified language detection, adjustable subtitle limits, and optional transcript JSON output.

Key features

  1. 01Transcribes audio and video
  2. 02Auto-detects or accepts a language
  3. 03Configures subtitle length and timing
  4. 04Exports SRT subtitles
  5. 05Optionally outputs timestamped JSON

Use cases

  1. 01Creating subtitles for a video
  2. 02Transcribing audio in a specified language
  3. 03Adjusting subtitle segments for readability
  4. 04Saving word-level transcript timestamps

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/aviz85/claude-skills-library --skill transcribe

After installing, type/transcribein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

SETUP.md
scripts/
.env.example
package.json
transcribe.ts
tsconfig.json

Details

From the project README

Transcribe

First time? If setup_complete: false above, run ./SETUP.md first, then set setup_complete: true.

Generate SRT subtitle files from audio/video using ElevenLabs Scribe v2.

Quick Start

cd ~/.claude/skills/transcribe/scripts

# Basic transcription (auto-detect language)
npx ts-node transcribe.ts -i /path/to/video.mp4 -o /path/to/output.srt

# Specify language
npx ts-node transcribe.ts -i /path/to/video.mp4 -o /path/to/output.srt -l en

# Custom subtitle length (max words per entry)
npx ts-node transcribe.ts -i /path/to/video.mp4 -o /path/to/output.srt --max-words 6

# Custom max duration per subtitle
npx ts-node transcribe.ts -i /path/to/video.mp4 -o /path/to/output.srt --max-duration 4.0

Options

OptionShortDefaultDescription
--input-i(required)Input audio/video file
--output-o(required)Output SRT file path
--language-lautoLanguage code (en, he, ar, etc.)
--max-words5Max words per subtitle entry
--max-duration3.0Max seconds per subtitle entry
--max-chars70Max characters per subtitle entry
--timing-offset0.25Timing offset in seconds
--jsonfalseAlso output raw transcript JSON

Language Codes

  • en - English
  • he - Hebrew
  • ar - Arabic
  • es - Spanish
  • fr - French
  • de - German
  • ru - Russian
  • zh - Chinese
  • ja - Japanese
  • (or omit for auto-detection)

Output

The script generates:

  1. .srt file - Standard subtitle file
  2. .json file (optional) - Raw transcript with word-level timestamps

Environment

API key stored in scripts/.env:

ELEVENLABS_API_KEY=your_key_here

Comments

Markdown supported