npm

openai-whisper

General-purpose speech recognition model for converting audio to text

brewmacoslinux
Try with needOr install directly
Source

About

General-purpose speech recognition model

Commands

whisper

Examples

Transcribe an audio file to text$ whisper audio.mp3
Transcribe with specific language and output format$ whisper audio.wav --language en --output_format txt
Transcribe using a specific model size$ whisper audio.m4a --model base