Transcribe Audio with Whisper

Install and transcribe

pip install -U openai-whisper

import whisper
model = whisper.load_model("base")
result = model.transcribe("meeting.mp3")
print(result["text"])

Choosing a model size

Whisper ships in sizes from tiny to large. Bigger models are more accurate but slower and need more memory. base or small is a great balance for most laptops; reach for large when accuracy matters and you have a GPU. It handles dozens of languages and can translate to English too.