Whisper Transcription

Overview

Transcribe audio/video files to text using OpenAI Whisper — either locally (free, no API key) or via the API.

Local Whisper (no API key)

Install

pip install openai-whisper
# or with conda:
conda install -c conda-forge openai-whisper

Transcribe

whisper audio.mp3 --model medium --output_format txt
whisper audio.m4a --model small --language fr --output_format srt