llm

Lets use some ai magic to transcribe audio in the command line. simple enough with whisper https://github.com/openai/whisper whisper audiofile.m4a --language English --model medium and then there is the python version which is oktoo import whisper model = whisper.load_model("base") result = model.transcribe("audio.mp3") print(result["text"]) I have had pretty good results with it but i think that i like the ui better for a simple macos app called whisper transcription. there is a paid tier but the free one is good enough for me....