ElevenLabs Transcription Tool

A TypeScript tool for batch transcribing audio/video files using the ElevenLabs Speech-to-Text API.

Setup

1. Install dependencies:

   npm install

2. Create a .env file with your ElevenLabs API key:

   cp .env.example .env
   # Edit .env and add your API key

3. Add audio/video files to the to transcribe folder

Usage

1. Development mode (with TypeScript compilation):

   npm run dev

2. Production mode (compile first, then run):

   npm run build
   npm start

Features

• Supports all major audio/video formats (mp3, wav, m4a, flac, ogg, mp4, mov, avi, mkv)
• Outputs JSON transcription files next to source files with same name
• Includes speaker diarization and audio event tagging
• Batch processes all files in the to transcribe folder

Scripts

• npm run build - Compile TypeScript to JavaScript
• npm run dev - Run in development mode with ts-node
• npm start - Run compiled JavaScript
• npm run lint - Check code style
• npm run lint:fix - Fix linting issues
• npm run format - Format code with Prettier
• npm run check - Run TypeScript check and linting

Output Format

Each audio file generates a JSON file containing:

• text: Full transcription text
• language_code: Detected language
• language_probability: Confidence in language detection
• words: Array of word objects with timestamps and speaker information