←back to thread

OpenAI charges by the minute, so speed up your audio

(george.mand.is)
678 points georgemandis | 4 comments | 25 Jun 25 13:17 UTC | HN request time: 0.722s | source
Show context
rob ◴[25 Jun 25 16:20 UTC] No.44379019[source]▶
For anybody trying to do this in bulk, instead of using OpenAI's whisper via their API, you can also use Groq [0] which is much cheaper:

[0] https://groq.com/pricing/

Groq is ~$0.02/hr with distil-large-v3, or ~$0.04/hr with whisper-large-v3-turbo. I believe OpenAI comes out to like ~$0.36/hr.

We do this internally with our tool that automatically transcribes local government council meetings right when they get uploaded to YouTube. It uses Groq by default, but I also added support for Replicate and Deepgram as backups because sometimes Groq errors out.

replies(5): >>44379183 #>>44380152 #>>44380182 #>>44381963 #>>44384523 #
1. georgemandis ◴[25 Jun 25 16:35 UTC] No.44379183[source]▶
Interesting! At $0.02 to $0.04 an hour I don't suspect you've been hunting for optimizations, but I wonder if this "speed up the audio" trick would save you even more.

> We do this internally with our tool that automatically transcribes local government council meetings right when they get uploaded to YouTube

Doesn't YouTube do this for you automatically these days within a day or so?

replies(3): >>44379336 #>>44380033 #>>44380071 #
2. rob ◴[25 Jun 25 16:46 UTC] No.44379336[source]▶
> Doesn't YouTube do this for you automatically these days within a day or so?

Oh yeah, we do a check first and use youtube-transcript-api if there's an automatic one available:

https://github.com/jdepoix/youtube-transcript-api

The tool usually detects them within like ~5 mins of being uploaded though, so usually none are available yet. Then it'll send the summaries to our internal Slack channel for our editors, in case there's anything interesting to 'follow up on' from the meeting.

Probably would be a good idea to add a delay to it and wait for the automatic ones though :)

3. jerjerjer ◴[25 Jun 25 17:53 UTC] No.44380033[source]▶
> I wonder if this "speed up the audio" trick would save you even more.

At this point you'll need to at least check how much running ffmpeg costs. Probably less than $0.01 per hour of audio (approximate savings) but still.

4. ks2048 ◴[25 Jun 25 17:56 UTC] No.44380071[source]▶
> Doesn't YouTube do this for you automatically these days within a day or so?

Last time I checked, I think the Google auto-captions were noticeably worse quality than whisper, but maybe that has changed.