Gregory's ServerWrote a tiny new LLM plugin this morning: llm-whisper-api, which lets you do this (if you have an OpenAI API key configured already):
llm install llm-whisper-api
llm whisper-api myfile.mp3 > transcript.txt
 9 comments
@ame I got Claude to port my Whisper API plugin to use Groq instead! It seems to work - I've only released it as an alpha though as I've not yet added automated tests or manually QAd all of the options https://github.com/simonw/llm-groq-whisper  @ame I got Claude to make an artifact for that instead, looks like it might work OK https://gistpreview.github.io/?e29943852f371f638c9a3ae1dcc4784e Claude transcript: https://gist.github.com/simonw/49b52ce2a7b5796edf4e0e2e2152db41 |
@simon In principle, human transcription as a job or service is also dead.
I've always wished for something like this to turn podcasts into texts.
Had played around with opensource like cmusphinx a long time ago. But the quality wasn't particularly good then and it was also very slow. It's impressive how it has developed.