Whisper MP3 to SRT Converter

A minimal, elegant CLI tool to convert audio files to SRT subtitle format using OpenAI's Whisper API.

Features

• Convert audio files (MP3, MP4, MPEG, MPGA, M4A, WAV, WEBM) to SRT subtitles
• Clean, simple Python implementation
• Uses OpenAI's official Whisper API
• Automatic timestamp generation

Installation

1. Clone this repository or download the files

2. Install dependencies:

pip install -r requirements.txt

3. Set up your OpenAI API key:

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

Or create a .env file:

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

Usage

Basic usage (output will be saved as audio.srt):

python whisper_to_srt.py audio.mp3

Specify custom output path:

python whisper_to_srt.py podcast.mp3 subtitles.srt

Use as a Python module:

from whisper_to_srt import convert_to_srt

# Convert with default settings
convert_to_srt("podcast.mp3")

# Specify output path
convert_to_srt("podcast.mp3", "output/subtitles.srt")

# Use custom API key
convert_to_srt("podcast.mp3", api_key="sk-...")

Requirements

• Python 3.10+
• OpenAI API key with access to Whisper API
• Audio file in supported format (MP3, MP4, MPEG, MPGA, M4A, WAV, WEBM)

Pricing

OpenAI Whisper API pricing is $0.006 per minute of audio (as of 2024).

License

MIT