←back to thread

OpenAI charges by the minute, so speed up your audio

(george.mand.is)
678 points georgemandis | 7 comments | 25 Jun 25 13:17 UTC | HN request time: 0.276s | source | bottom
Show context
georgemandis ◴[25 Jun 25 13:17 UTC] No.44376990[source]▶
I was trying to summarize a 40-minute talk with OpenAI’s transcription API, but it was too long. So I sped it up with ffmpeg to fit within the 25-minute cap. It worked quite well (Up to 3x speeds) and was cheaper and faster, so I wrote about it.

Felt like a fun trick worth sharing. There’s a full script and cost breakdown.

replies(1): >>44378167 #
1. bravesoul2 ◴[25 Jun 25 15:03 UTC] No.44378167[source]▶
You could have kept quiet and started a cheaper than openai transcription business :)
replies(4): >>44378890 #>>44379081 #>>44379840 #>>44380550 #
2. behnamoh ◴[25 Jun 25 16:09 UTC] No.44378890[source]▶
Sure, but now the world is a better place because he shared something useful!
3. 4b11b4 ◴[25 Jun 25 16:25 UTC] No.44379081[source]▶
Pre-processing of the audio still a valid biz, multiple types of pre-processing might be valid
4. hn8726 ◴[25 Jun 25 17:33 UTC] No.44379840[source]▶
Or openai will do it themselves for transcription tasks
5. ilyakaminsky ◴[25 Jun 25 18:39 UTC] No.44380550[source]▶
I've already done that [1]. A fraction of the price, 24-hour limit per file, and speedup tricks like the OP's are welcome. :)

[1] https://speechischeap.com

replies(1): >>44382158 #
6. bravesoul2 ◴[25 Jun 25 21:55 UTC] No.44382158[source]▶
Nice. Don't expect you to spill the beans but is it doing OK (some customers?)

Just wondering if I cam build a retirement out of APIs :)

replies(1): >>44384932 #
7. ilyakaminsky ◴[26 Jun 25 07:04 UTC] No.44384932{3}[source]▶
It's sustainable, but not enough to retire on at this point.

> Just wondering if I cam build a retirement out of APIs :)

I think it's possible, but you need to find a way to add value beyond the commodity itself (e.g., audio classification and speaker diarization in my case).