OpenAI charges by the minute, so speed up your audio • Hacker News Board

Re: OpenAI charges by the minute, so speed up your audio

#231

Post by niutech » Mon, Jun 30, 2025, 1:14 AM UTC

w-m wrote: post #13

With transcribing a talk by Andrej, you already picked the most challenging case possible, speed-wise. His natural talking speed is already >=1.5x that of a normal human. One of the people you absolutely have to set your YouTube speed back down to 1x when listening to follow what's going on. In the idea of making more of an OpenAI minute, don't send it any silence. E.g. ffmpeg -i video-audio.m4a \ -af "silenceremove=…

Or the OP could just use NotebookLM for free, which has text & video summarization built-in, without need for any trimming.

Re: OpenAI charges by the minute, so speed up your audio

#232

Post by ada1981 » Thu, Jul 03, 2025, 2:50 AM UTC

appleaday1 wrote: post #27

ada1981 wrote: post #3

We discovered this last month. There is also prob a way to send a smaller sampler of audio at diff speeds and compare them to get a speed optimization with no quality loss unique for each clip.

source?

Oh I wasn’t trying to take credit for it, we just discovered we could do this last month and assumed it was widely known and implemented it.

I could find a screen shot of our internal texts I suppose, but we didn’t publish anything on it.

Re: OpenAI charges by the minute, so speed up your audio

#233

Post by ada1981 » Thu, Jul 03, 2025, 2:51 AM UTC

moralestapia wrote: post #14

ada1981 wrote: post #3

We discovered this last month. There is also prob a way to send a smaller sampler of audio at diff speeds and compare them to get a speed optimization with no quality loss unique for each clip.

>We discovered this last month. Nice. Any blog post, twitter comment or anything pointing to that?

We didn’t think to publish it; it actually seemed so obvious I assumed it was a widely known thing.

We were developing an AI that processes someone’s Instagram profile (reels, comments, etc.) and provided insights and realized we could 2x the audio to cut time and costs.

Re: OpenAI charges by the minute, so speed up your audio

#234

Post by ilyakaminsky » Tue, Jul 08, 2025, 4:16 PM UTC

satvikpendem wrote: post #218

ilyakaminsky wrote: post #87

Earlier quoted context omitted.

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

Can it do real-time transcription with diarization? I'm looking for that for a product feature I'm working on. Currently I've seen Speechmatics do this well, haven't heard of others.

Not yet. The gains in efficiency come from optimizing the speedup factor. Real-time audio cannot be processed any faster than 1× by definition.