Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI charges by the minute, so speed up your audio

george.mand.is

Post reply on HN
Print view View original

171–180 of 234 posts

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

#171

Post by dajonker »

Gemini 2.5 pro is, in my usage, quite superior for high quality transcriptions of phone calls, in Dutch in my case. As long as you upload the audio to GCS there you can easily process conversations of over an hour. It correctly identified and labeled speakers.

The cheaper 2.5 flash made noticeably more mistakes, for example it didn't correctly output numbers while the Pro model did.

As for OpenAI, their gpt-4o-transcribe model did worse than 2.5 flash, completely messing up names of places and/or people. Plus it doesn't label the conversation in turns, it just outputs a single continuous piece of text.

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

#173

Post by weird-eye-issue »

Raphell wrote: post #172
weird-eye-issue wrote: post #161

Earlier quoted context omitted.

Can we ban this "person" for AI replies?

I get it. But I'm just someone who likes to think things through and say them simply.

You aren't saying anything simply. You are verbosely saying nothing.

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

#175

Post by tucnak »

maxall4 wrote: post #98
janalsncm wrote: post #76

Earlier quoted context omitted.

> I wonder if there's a way to automatically detect how "fast" a person talks in an audio file Transcribe it locally using whisper and output tokens/sec?

Just count syllables per second by doing an FFT plus some basic analysis.

> FFT plus some basic analysis

Yeah, totally easier than `len(transcribe(a))/len(a)`

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

#176

Post by quietbritishjim »

nickjj wrote: post #119
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=…

Andrej's talk seemed normal to listen at 2x but I've also listened to everything at 2x for a long time. Unfortunately a byproduct of listening to everything at 2x is I've had a number of folks say they have to watch my videos at 0.75x but even when I play back my own videos it feels painfully slow unless it's 2x. For reference I've always found John Carmack's pacing perfect / natural and watchable at 2x too. A recent…

Your actual speed of talking sounds a little faster than average but not notably so.

But it feels (very subjectively) faster to me than usual because you don't really seem to take any pauses. It's like the whole video is a single run-on sentence that I keep buffering, but I never get a chance to process it and flush the buffer.

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

#177

Post by phito »

w-m wrote: post #103
squigz wrote: post #93

Earlier quoted context omitted.

Out of curiosity, how might you improve those docs? They seem fairly reasonable to me

The documentation reads like it was written by a programmer who documented the different parameters to their implementation of a specific algorithm. Now when you as the user come along and want to use silenceremove, you'll have to carefully read through this, and build your own mental model of that algorithm, and then you'll be able to set these parameters accordingly. That takes a lot of time and energy, in this cas…

> naming things is famously one of the two hard problems in computer science

Isn't ffmpeg made by a French person? As a francophone myself, I can tell you one of the biggest weakness of francophone programmers is naming things, even worse when it's in English. Maybe it's what's at play here.

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

#178

Post by ada1981 »

w-m wrote: post #103
squigz wrote: post #93

Earlier quoted context omitted.

Out of curiosity, how might you improve those docs? They seem fairly reasonable to me

The documentation reads like it was written by a programmer who documented the different parameters to their implementation of a specific algorithm. Now when you as the user come along and want to use silenceremove, you'll have to carefully read through this, and build your own mental model of that algorithm, and then you'll be able to set these parameters accordingly. That takes a lot of time and energy, in this cas…

Curious if this is helpful.

https://claude.ai/public/artifacts/96ea8227-48c3-484d-b30b-6...

I had Claude rewrite the documentation for silenceremove based on your feedback.

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

#179

Post by jwrallie »

d1sxeyes wrote: post #164
jwrallie wrote: post #159

Earlier quoted context omitted.

From my own experience with whisper.cpp, normalizing the audio and removing silence not only shortens the process time significantly, but also increases a lot the quality of the transcription, as silence can mean hallucinations. You can do that graphically with Audacity too, if you do not want to deal with the command line. You also do not need any special hardware to run whisper.cpp, with the small model literally a…

1/3 of the meeting is silence? That’s a good thing. It’s allowing people time to think over what they’re hearing, there are pauses to allow people to contribute or participate. What do you think a better percentage of silent time would be?

Good point, somehow if I think of a 30 minutes meeting, 10 minutes of silence sounds great, but seeing a 1 hour block disappear from a 3 hour recording makes me want to use that “free” hour to do something else.

Well, I don’t think silence is not the real problem with a 3 hour meeting!

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

#180

Post by lordspace »

karpathy wrote: post #57

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. ;)

that's a really good summary :)
Post reply on HN