Speech to Text Transcription

Simple Python script to transcribe audio files using OpenAI's API with word-level timestamps.

Setup

1. Install dependencies:

pip install -r requirements.txt

2. Set your OpenAI API key:

export OPENAI_API_KEY="your-api-key-here"

Or create a .env file:

OPENAI_API_KEY=your-api-key-here

Usage

python transcribe.py <audio_file> [output_file]

Examples

# Transcribe audio.mp4 and save to audio.txt
python transcribe.py audio.mp4

# Transcribe audio.mp4 and save to custom output file
python transcribe.py audio.mp4 output.txt

Features

• Supports MP4, MP3, WAV, and other audio formats
• Word-level timestamps (character-aware)
• Simple command-line interface
• Automatically saves transcriptions to text files

Output Format

When using word-level timestamps, the output includes:

• Full transcript text
• Word-level timestamps with start and end times