Show HN: Scriber Pro – Offline AI transcription for macOS

How does it compare to MacWhisper?

MacWhisper crashes at about an hour of context. This uses, smart, invisible regex in the text generation pipe. Makes this fast. + bonus, there is no context limit

The landing page is difficult to read due to the strong red background.

Word level timestamps?

Is there a reason it requires macOS 26?

Smart invisible regex makes it fast and prevents it from crashing? What does that mean?

You use the word "transcribe" but the page doesn't appear to support that claim? This looks like straightforward STT? Or does it actually support transcription (diarization, etc.)?

(Also, the text is completely illegible on your site.)

Thank you. I have heard this : P - It will change soon.

What languages does this support? Does it support switching between multiple languages in one video?

For example, could it support a video that included spoken Latin, ancient Greek, German, and Italian?

I vibecoded a similar app. Here’s the open source link, if folks want to build their own:

https://github.com/naveedn/audio-transcriber

Tahoe really is just unusable

Uses liquidGlass fairly heavily- just design reasons-- I'm happy to expand compatibility

Does it support speaker diarization?

Hence why I'm asking why it requires it. Trying to hold off as long as I can!

At $3.99 this was an instant buy for me until the App Store told me I couldn't. I think the venn diagram between HN users and those holding off on Tahoe is probably a pretty big overlap. ;-)

Thanks. An update that will add functionality that allows a user to give it a link that contains web video, will do dynamic link discovery (with Safari extension, and pull in the video automatically (M3U8 discover and retrieval) -- Lots of online lecture videos that need transcription.

I will include better version support (probably to os 13).

I learned this as a young developer writing status pages. I had a colour-blind colleague, so text on green/yellow/red.

Typically white text works better on red.

Seconding/thirding the request for diarization! I would use this as my main transcription app if it had that.

r/#FF0000_rage

I've done 3+hours with MacWhisper without issue? One downside is the transcription is not real time - can Scriber Pro do realtime?

eng der fr de es it pt ru zh ko ar and ja

Slower

I've been using MacWhisper for this, with a huge variety of transcription options and things like speaker detection. It works great for all the 1 hour and shorter videos I've fed it, but does this have more to offer?

I haven't tried a 4+ hour video with MacWhisper but I presume that would work the same.

Yours isn't OSS, meaning I have no idea what I'm running

Can you clarify your question

That page has a very aggressive background color and really low contrast. Extremely annoying.

"Smart, invisible regex" sounds like a lot of bs... could you give a more technical explanation?

Also the Whisper model doesn't really have a context window, it already segments the audio with a certain amount of overlap between the chunks, I really have a hard time understanding what you are trying to say here.

I use it as my own transcription app, I really do love it ( biased I know, but genuinely)

OSS would be incredibly slow, also seems like overkill for this use case

My eyes, my eyes! What is this red colour?

Cool project, I am using ChatGPT for recording/summarising meetings but the limit there is 2 hours

Thank you ! I think I was actually going for that

Seems like a great app, but I have to ask:

https://scriberpro.cc/about/ Are you trolling people with this page's design? Unreadable colors AND a wobble effect? :D

What does that even mean? Why would OSS make it slower? Why would it be an overkill? This is not Producthunt, you have to give at least some kind of explanation for your claims.

reading on drugs simulator?

I think they are trying to do something like select a word in the transcript and be take straight to the point in the video that said word was spoken

Whisper will fail > 99%* (edit, most of the time) of the time at lengths over 90 minutes and fairly high over one hour.

MY EYES

This is just plain wrong. I have my own Whisper App in the AppStore (on iOS, with very limited memory capacity) and there are no problems at all with longer Audio / Video files.

Please be my guest to test my claims. No tall tales here!

I was going to buy the app, but these responses are putting me off massively. How would making it OSS slow it down?

What is your tech stack to make this? Is it end to end swift?

Ah, I think you're asking if a user can, when wanting timestamps, if they can further edit the output to be by word? Currently set around each sentence (2-5s) --- But that is absolutely doable and that’s a great idea - On the next update (~3-4wks) I’ll definitely include the ability to control that.

Red was a bold choice ill admit

Yes, but by a negligible margin. My program is designed for multi-track audio, which means I run this in parallel on multiple 3 hour recordings, and get results in 12 minutes.

You haven’t shared any architectural details. What model? What size? How can anyone be sure that what you’re building is truly offline?

https://i.imgur.com/EBaMNDS.png This is how your landing page looks on my desktop.

The first thought I had when it loaded was, "Did we forget how to make webpages?"

Sorry. I'm sure the software is great, but yeah.

I've never had whisper complete a single attempt a anything over 75 min

So, can it handle multiple languages in one video, or do you need to segment the different languages using LID first? This has been a thorny issue for people working in multilingual audio (there are at least two or three of us).

This is absolutely not my experience. I regularly (weekly at least) use whisper for 90-120 minutes pieces of content and only rarely have problems.

Question: can it discern (and label) different speakers? If so, could you kindly share the limit on speakers per video?

That my friend, is just one of the annoying bottlenecks, that inspired me to do this

Also that color is color(display-p3 .768627 .031373 .031373 / 1)- It is actually technically redder than red actually is

You can also run Whisper locally in your browser for free: https://ggml.ai/whisper.cpp/

I haven't test that specific edge case, I'm sorry. I tested 2 langue's having a normal conversation and that worked fine- "Auto or English" handle multiple lan the best

The red looks great. Takes me back to the old days.

I honestly thought it would be nothing more than a fun little easter egg, Red was a bold choice I admit. ! I will making a css update soon

Also, disabling scrolling and using swipe for sections instead _at a font size that causes text to overflow_, depending on phone screen size, meaning a bunch of the site is _literally_ unreadable, since it's off the screen with no way to get there.

I suspect, from the responses of the creator here, that this app they are selling is likely violating a number of open source licenses…

Any way to access this with python so I can use it programmatically?

If ever there were a reason to upgrade!

But thats a fair point- I drank the Liquid Glass Kool-Aid----- I'll aim more compatibility the next upgrade

This isn't run using Python, but also no

I’ve used whisper-cop on 5-hour podcasts without problems.

Would also love to hear what you mean by “smart invisible regex,” sounds like AI slop to me.

MacWhisper handles multiple-hour-long recordings just fine for me. I regularly process 4hrs on MacWhisper. Even whisper-cpp works fine these days for long recordings too.

Cool product, but it would be better if you stopped spreading misinformation to support it.

No need to apologize!

Oh I see title ate your h2 text. Thats no good. Thanks for showing me

Great when you have time to kill and not a lot to process I suppose

What do you mean context limit?

Neither whisper nor MacWhisper have any context limit

You are looking for speaker diarization. No one is doing this well currently on device (in macOS land at least).

Timecode drift is an interesting issue, think I faced this recently while translating a Google Meet transcript into an incident report timeline.

The elapsed-time timestamps didn't correlate well with other data sources. I figured it was a mistake on my end, and just brushed it off.

OSS as in open source software. Not Open Sound System. Just in case.

Do you have a mailing list?

No, not yet! That will definitely be included in the next update next month. Thank you for reminding me of peoples unique need for this use case

You were going for *really low contrast* ? That's an interesting goal to have.

Reds people choose are usually between dark and light, which doesn't contrast particularly well on anything because for good contrast you need a dark color vs a light color.

Green, yellow, red or whatever hue is fine, as long as it's dark or light enough. Colorblind and non-colorblind people can see how dark or light a color is (luminance), but they might not agree on the hue. That's why WCAG contrast checks require luminance contrast and not hue contrast.

It's best to use a contrast checker because it's not always intuitive how dark or light a color is e.g. yellow and lime are almost as light as white.

I can’t read this site. Red background, dark grey/black text, is a terrible terrible choice for colors for readability. There were some words there but all I could make out were the header on my mobile phone.

Can you back up your claim that it's slow?

the obnoxious site deisgn and comments like this stopped me from clicking buy in the apple store

Same! I was trying to buy but wasn't able to.

Swift 37.0% C++ 26.5% C 19.8% Rust 4.7% Shell 4.4% Objective-C 1.7% Other 5.9%

> MacWhisper crashes at about an hour of context.

This is not true. (I've been a MacWhisper user since 2023. I have two bugs during that time, which the author addressed quickly.)

I am a MacWhisper Pro user, and I successfully transcribed and translated a 15-hour course inside the app without any issues

MacWhisper Pro supports this, if your need for this is time-sensitive. https://macwhisper.helpscoutdocs.com/article/32-automatic-sp...

Due to overwhelming response,

https://iili.io/KkoKBCx.png

I have change the bg color

They also mean the 3D effect (and there's also a blur one)

One thing that Rev and other online services have as well as MacWhisper is a good interface for editing the text to correct inevitable errors. Being able to click on the text and have it sync to the correct place in the audio is a must for my use case of transcribing interviews. Also speaker diarization.

I sort of use SuperWhisper, it is sort of good. https://superwhisper.com/

Scribers’ iCloud system automatically backs up each transcription and organizes them in a three-pane folder view—somewhat inspired by Bars’ layout. This structure allows a surprising degree of customization for all your data needs, especially when transcribing interviews. It would probably make for a very comfortable workflow here

Does it do separate speaker identification (diarization)?

What's the stack, if I may ask? (I believe Whisper-X does the diarization thing)

Can't really declare that without declaring which whisper model in particular you are referring to, as there are a number of them

> Smart invisible regex

I've never heard a regex person speak this way of a regex.

Please tell me you didn't vibecode the regex... one of the areas it's still not good at

[stub for offtopicness]

App Store link no longer works. Willing to try/purchase but it's nowhere available. AppStore search doesn't return "Scriber Pro" either.

Thanks.

As a side project, I just launched a privacy-first web-based meeting transcriber (https://basilai.app/app). Everything runs entirely in your browser — both the transcription and AI summarization — so no audio or text ever leaves your device.

I'm using the browser built in transcription service plus downloading a model and running it via webgpu. No login. At the end of your meeting, you get a zip file with the audio, transcript and summary.

> Cool product, but it would be better if you stopped spreading misinformation to support it.

I don’t see this sort of thing, has the page changed? Edit: the comments here…

The drop shadow on the pages does make it deeply unpleasant to read.

Nice work. What model did you use and do you ship the model with a base distribution or is it downloaded with the app?

My experience share only supporting the latest OS:

I have launched apps focused on a new feature in the latest OS and regretted it. The # of people who have the latest OS is much smaller than the full install base for much longer than I thought. As a result, my marketing conversion was unnaturally low - people who liked the app idea but couldn't install because they had the wrong OS. This causes two problems: potential users I activated but couldn't convert and this signal gets internalized by the App Store, pushing down future impressions.

Now I always have a fallback implementation of the feature so I can target the prior OS. Both Mac and iOS.

What language do you have the model architecture and implementation in? Feel like it would be the biggest proportion of the codebase, curious if you did it in Swift?

Will it transcribe audio in Czech (in future versions)?

Actually I would be happy if it could just identify occurrences (timestamps) of a specific word or a small set of words.

Too bad it requires that unspeakable abomination macOS 26. No can do.

FYI it works now because I just brought it up. The website mentions there were HN promo/discount codes, so I honestly expected the app to be like $20+, so color me shocked when it's $3.99.

I haven't worked in a while with transcription, but whisper.cpp itself (which I assume is the underlying tech behind MacWhisper) does realtime transcription on my MBP with an M1 Pro chip. When I first started writing my last completed novel, I fired it up and just started telling the story to test it out. Realtime.

That was back in 2023. I assume things work better now.

Wanted to buy. Not on Macos 26.

So weird that this is nowhere stated on the website at all. Was literally the first and only thing I was interested in. So bad.

What libraries/models is this built on?

Probably NVIDIA’s Parakeet-TDT-0.6b-v3.

Is it only for English? is CLI available? There are thousands of files on my local and I'd like to save results to local db. Thanks!

Not gonna lie, the pricing is super attractive! :) I'd love to see an API, so I can also run automations using this tool on my mac.

Also look at Vibe:

It even supports speaker differentiation/recognition and is open source on mac/windows/linux;

https://github.com/thewh1teagle/vibe

FYI: Still doesn't redirect... Had to remove the url query params. Only https://apps.apple.com/us/app/scriber-pro/id6751968220 worked as expected.

Thanks for sharing.

Looking forward to the "Speaker Detection" feature release. ;)

It uses whisper, but also directly calls other tools and puts everything under one nice Gui

I’ve also been pretty careful with sensitive recordings, so the offline part really stands out to me. This looks great.

Or in the cloud tbh

Wow, it's a very pleasant price.

A week later and, as of this morning it’s number six in the top 10 paid utilities app on the MacApp Store

I’m glad all the feedback so far has been very positive. Thanks everyone !

Oh and it supports MacOs15.6 now too