←back to thread

685 points georgemandis | 1 comments | | HN request time: 0.263s | source
Show context
karpathy ◴[] No.44379755[source]
Omg long post. TLDR from an LLM for anyone interested

Speed your audio up 2–3× with ffmpeg before sending it to OpenAI’s gpt-4o-transcribe: the shorter file uses fewer input-tokens, cuts costs by roughly a third, and processes faster with little quality loss (4× is too fast). A sample yt-dlp → ffmpeg → curl script shows the workflow.

;)

replies(3): >>44379800 #>>44379806 #>>44386599 #
1. bravesoul2 ◴[] No.44379800[source]
This is the sort of content I want to see in Tweets and LinkedIn posts.

I have been thinking for a while how do you make good use of the short space in those places.

LLM did well here.