Show HN: Scriber Pro – Offline AI transcription for macOS

Hey HN! Built this because I was tired of waiting hours for transcription services and didn't want to upload sensitive recordings to the cloud.

  Real metrics from my M1 Max: 4.5hr video file transcribed in 3 minutes 32
  seconds. Works completely offline.

   First 5 HN users who click the button on the page get it free. Literally promo code straight to the app sore  


  Key differences vs Rev/Otter:
  - No 2-hour file limits (handles any length)
  - Timecodes stay accurate on long files (no drift from chunking)
  - Supports MP3, WAV, MP4, MOV, M4A, FLAC
  - Exports to SRT, VTT, JSON, PDF, DOCX, CSV, Markdown

  Built for macOS. Happy to answer questions!
scriberpro.cc

・

135 points

・

rezivor

・

3 days ago

117 comments

geerlingguy ・ 3 days ago

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.

  • rezivor ・ 3 days ago

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

    • gcr ・ 3 days ago

      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.

      • lostlogin ・ 3 days ago

        > 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.

busymichael ・ 3 days ago

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.

xnx ・ 3 days ago

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

  • rezivor ・ 3 days ago

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

Telemakhos ・ 3 days ago

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?

  • runxel ・ 3 days ago

    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.

  • rezivor ・ 3 days ago

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

    • Telemakhos ・ 3 days ago

      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).

      • rezivor ・ 3 days ago

        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

yewenjie ・ 3 days ago

Does it support speaker diarization?

torstenvl ・ 3 days ago

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.)

  • rezivor ・ 3 days ago

    r/#FF0000_rage

mattstudio ・ 3 days ago

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.

  • rezivor ・ 3 days ago

    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

CrazyCatDog ・ 3 days ago

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

  • oidar ・ 3 days ago

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

    • shloky ・ 2 days ago

      Or in the cloud tbh

  • rezivor ・ 3 days ago

    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

scilro ・ 3 days ago

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

  • rezivor ・ 3 days ago

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

der_philipp ・ 2 days ago

Also look at Vibe:

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

https://github.com/thewh1teagle/vibe

  • der_philipp ・ 2 days ago

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

pmarreck ・ 3 days ago

Does it do separate speaker identification (diarization)?

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

nvdnadj92 ・ 3 days ago

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

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

  • rezivor ・ 3 days ago

    Slower

    • nvdnadj92 ・ 3 days ago

      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?

    • ramon156 ・ 3 days ago

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

      • rezivor ・ 3 days ago
        ・ 8 more

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

        • mpeg ・ 3 days ago

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

        • kamranjon ・ 3 days ago

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

        • user- ・ 3 days ago

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

        • fl_rn_st ・ 3 days ago

          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.

        • konart ・ 3 days ago

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

        • ideashower ・ 3 days ago

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

oasisbob ・ 3 days ago

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.

nubg ・ 3 days ago

How does it compare to MacWhisper?

  • rezivor ・ 3 days ago

    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

    • barapa ・ 3 days ago

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

    • grosswait ・ 3 days ago

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

      • KPGv2 ・ 3 days ago

        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.

    • fady0 ・ 3 days ago

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

    • CharlesW ・ 3 days ago

      > 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.)

    • fl_rn_st ・ 3 days ago

      "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.

      • rezivor ・ 3 days ago
        ・ 6 more

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

        • saaaaaam ・ 3 days ago

          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.

        • fl_rn_st ・ 3 days ago
          ・ 2 more

          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.

          • rezivor ・ 3 days ago

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

        • pmarreck ・ 3 days ago

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

        • gcr ・ 3 days ago

          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.

    • pmarreck ・ 3 days ago

      > 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

    • gcr ・ 3 days ago

      What do you mean context limit?

      Neither whisper nor MacWhisper have any context limit

masonkim25 ・ 2 days ago

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

cassettelabs ・ 3 days ago

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.

jiriro ・ 3 days ago

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.

mattfrommars ・ 3 days ago

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

  • rezivor ・ 3 days ago

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

    • CaptainOfCoit ・ 3 days ago

      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?

xjlin0 ・ 3 days ago

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!

vladsanchez ・ 3 days ago

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

Thanks.

  • KPGv2 ・ 3 days ago

    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.

aquir ・ 3 days ago

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

  • rezivor ・ 3 days ago

    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

FitchApps ・ 3 days ago

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

  • woodson ・ 3 days ago

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

trvr ・ 3 days ago

Is there a reason it requires macOS 26?

  • rezivor ・ 3 days ago

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

    • trvr ・ 3 days ago

      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. ;-)

      • nkotov ・ 3 days ago

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

      • rezivor ・ 3 days ago
        ・ 3 more

        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

        • busymichael ・ 3 days ago

          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.

        • polarix ・ 3 days ago

          Do you have a mailing list?

  • somberi ・ 3 days ago

    Wanted to buy. Not on Macos 26.

  • tomalbrc ・ 3 days ago

    Tahoe really is just unusable

    • rezivor ・ 3 days ago

      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).

    • trvr ・ 3 days ago

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

thedangler ・ 3 days ago

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

  • rezivor ・ 3 days ago

    This isn't run using Python, but also no

re ・ 3 days ago

What libraries/models is this built on?

brokensegue ・ 3 days ago

Word level timestamps?

  • rezivor ・ 3 days ago

    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.

  • rezivor ・ 3 days ago

    Can you clarify your question

    • qwertytyyuu ・ 3 days ago

      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

tempodox ・ 3 days ago

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

dang ・ 3 days ago

[stub for offtopicness]

  • heystefan ・ 3 days ago

    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

    • bazzargh ・ 3 days ago

      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.

    • qwertytyyuu ・ 3 days ago

      reading on drugs simulator?

    • rezivor ・ 3 days ago

      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

      • coldtea ・ 3 days ago

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

  • Oras ・ 3 days ago

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

    • rezivor ・ 3 days ago

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

      • ta1243 ・ 3 days ago
        ・ 2 more

        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.

        • seanwilson ・ 3 days ago

          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.

  • reactordev ・ 3 days ago

    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.

  • SeanAnderson ・ 3 days ago

    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.

    • rezivor ・ 3 days ago

      No need to apologize!

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

  • jorgenbuilder ・ 3 days ago

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

  • iLoveOncall ・ 3 days ago

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

    • rezivor ・ 3 days ago

      Thank you ! I think I was actually going for that

      • ankit_mishra ・ 3 days ago

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