audio_transcribe

CLI tool for converting audio files to text using OpenAI's Whisper model with batch processing support.

completed
| devtools

Tech Stack

Python OpenAI Whisper Typer Rich

About

A Python command-line tool that streamlines audio-to-text conversion using OpenAI's Whisper technology. Features five model size options balancing speed versus accuracy, support for multiple audio formats (MP3, WAV, M4A, OGG, FLAC), language detection with optional specification, translation to English, and customizable output with JSON export including timestamps. Perfect for efficient batch processing of audio files.