Backlog

Next up

In Progress

Done

Main Roadmap

In Review

i am expecting android version of Blabby  AI  from you , Thank you

chethanonflow

I would love to share the modes that I've built with others and some of my learnings and as well see the modes other people have come up with. Call it the Mode Store if you will.

Modes Store/Share

Julian Gillespie

If the version you currently on is not working Please download the latest<h2></h2><h2><a target="" rel="noopener noreferrer nofollow" class="link" href="https://github.com/sumbatx15/blabby-updater/releases/download/1.2.0/blabby-1.2.0-setup.exe">Download BlabbyAI Windows v1.2.0</a></h2>To confirm you're using the latest version, check the top left corner of the settings window and make sure you see the version 1.2.0 there.

🐞Failed to transcribe🐞 ? Use the new version

BlabbyAI Dev

It would be amazing to have a keyboard app where you can type normally and also dictate text conveniently. It would be even better if it had different models you could prompt beforehand, just to easily write custom emails on the phone or have a fun conversation with friends where emojis are used automatically.

Phone keyboard app

Cosimo Lippe

Just a short note of appreciation and you have done a fantastic work. Let us know when this will be available in in Iphone and Android - I am willing to sign up and pay.

Thank you to the  Develop of Blabbyai

Algorithim codes

I might be wrong about this, but I tested it in a few different ways. It seems like if I have my taskbar set to automatically hide and Blabby is open, it prevents the taskbar from showing when I have any other app open full screen or across my whole window. So for instance, with Blabby on and enabled and my taskbar is set to automatically hide, If I open up Chrome and maximize that window, I can't get to my taskbar unless I minimize Chrome.

Windows desktop beta toolbar interferes with taskbar

Ry Keel

I had this idea about allowing users to choose different transcription APIs, like on cursor when you can choose different models … it would be interesting for advanced users that know subtle differences among them (such as, some are better at interpreting parts of a sentence that are spoken in a different language mid speech … some are better at translating tone to text, some are faster, etc)

Know which model is being used for transcription

Manu Castro

So, as far as I understand, the program is currently in active development, which is why you've made it free.But what about users who are already paying for a subscription to the browser extension of your product?For instance, I predict that this free limit of 10,000 credits will run out in about one and a half to two weeks for me. How will I continue to use your product then? Will it automatically switch to credits from the paid subscription once the free credits are used up? How is this functionality implemented?Or perhaps it would make more sense to give an option that if a user is already paying for a subscription, they wouldn’t need the free credits. What do you think?<img data-width="50%" data-align="left" data-featurebase-content-key="6749aff568c33a88d7b7547f/post/68148a3779ceec9e443010d2/01969039-5ae5-77a7-aa96-7f15e93fea70/b64u-aW1hZ2UucG5n.png" src="https://6749aff568c33a88d7b7547f.featurebase-attachments.com/c/post/68148a3779ceec9e443010d2/01969039-5ae5-77a7-aa96-7f15e93fea70/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260221T090000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260221%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=9e60f779ba9cde4aae074f80d1e90f8c92a63b61613ee33140a31b7e218bdaa4" data-featurebase-content-filename="image.png">

What should I do if I run out of the free 10,000 credits?

Web Traffic

As soon as I use any hotkeys—literally any of them—the app immediately stops working. The panel disappears and it no longer responds to any commands. The app itself and its settings still open without any issues, though. I have to restart the app, and even then it still doesn’t work.In the end, I switched back to version 1.4.5, which I’m using now without closing the app. But now I’m getting a bunch of pop-ups every few minutes telling me I need to close the app to update, and I don’t want to. Please add an option to not update the app and remove these annoying restart/update prompts.

It breaks after updating to version 1.5.0 when using hotkeys.

Иван

Please make the panel bar invisible when it hides so it doesn’t remain visible on the screen. Right now, when a video or game is in full-screen mode, you can still see a thin strip of a couple of pixels.

Make the panel bar invisible when it hides

I'd like to see an option in the software setup to set a different default model for transcription, just like what's done in the browser extension.Specifically, I'd love the ability to choose the “GPT-4o-transcribe” model, as it's much better at processing speech than the “Whisper” model.<img data-width="50%" data-align="left" data-featurebase-content-key="6749aff568c33a88d7b7547f/post/68148b22e3c705a378b5341e/0196903d-0648-7c85-bc55-ef4de19afd36/b64u-aW1hZ2UucG5n.png" src="https://6749aff568c33a88d7b7547f.featurebase-attachments.com/c/post/68148b22e3c705a378b5341e/0196903d-0648-7c85-bc55-ef4de19afd36/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260221T090000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260221%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=97dc5ee31c1b62c40097adb9da7f80262a6a532f6fc56fdcd805da22af4ff593" data-featurebase-content-filename="image.png">

Planned

The "GPT-4o-transcribe" model is set as the default for transcription.

I really wish you would create a feature that allows me to set my shortcut to a mouse click. For example, I’d like to click the scrollwheel and have it work to activate. It shouldn’t be limited to just the keyboard. Thanks, great product, i use it everyday

Allow mouse clicks in shortcurt

Ricardo Maranhão

During testing, I found an issue where, on Windows 11, if you use the menu hiding feature, the menu unfolds without any problem on the desktop.However, when, for example, Google Chrome is open, your program blocks the menu from opening.You can see this problem in more detail in the attached screencast: <a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://jmp.sh/7nx0vx51">https://jmp.sh/7nx0vx51</a>

The menu gets blocked when the browser or some other software is running

Please can we chnage the order of modes in the list.  If you have several "button" that are relating to a language (such as informal and formal text) it would be great to move them next to each other

Thomas Dahl

This is kinda annoying actually, if you already use this and just want to log into another machine, it keeps forcing you to do the tutorial and it seems that if you just close it, it does not register you user and you have to log in everyday again until you do the very exciting tutorial … seems a matter of just adding a ‘skip tutorial’ feature, hope it is.

Slightly annoying forced tutorial

Like offering an ElevenLabs integration. They just released Scribe v2 this week—specifically the base model that runs out of the box with no extra mods.Because when you test the base model—just standard transcription with no mods—and then compare it to a custom mod you’ve tuned, the difference is pretty noticeable: the base model mangles a lot of words and the transcription quality isn’t great.Cost-wise, I think OpenAI models and ElevenLabs are more or less in the same price range, and the integration there is probably just as straightforward as OpenAI’s. So if it’s possible, it’d be great to add this as an option in the app so you can choose the base transcription model—meaning not a model for custom mods, but the base Scribe model for transcription, which then gets processed by the models set up in the mods.Here’s a link to the new model from ElevenLabs:<a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://elevenlabs.io/blog/introducing-scribe-v2">https://elevenlabs.io/blog/introducing-scribe-v2</a>

Например, интеграция с ElevenLabs. На этой неделе они выпустили Scribe v2 — базовую модель, которая работает сразу после установки, без дополнительных модификаций.Потому что когда вы тестируете базовую модель — просто стандартную транскрипцию без модификаций — и затем сравниваете ее с настроенной вами модификацией, разница довольно заметна: базовая модель искажает много слов, и качество транскрипции не очень хорошее.С точки зрения стоимости, я думаю, что модели OpenAI и ElevenLabs находятся примерно в одном ценовом диапазоне, и интеграция там, вероятно, так же проста, как и в OpenAI. Поэтому, если это возможно, было бы здорово добавить эту опцию в приложение, чтобы можно было выбрать базовую модель транскрипции — то есть не модель для пользовательских модификаций, а базовую модель Scribe для транскрипции, которая затем обрабатывается моделями, настроенными в модификациях.Вот ссылка на новую модель от ElevenLabs:<a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://elevenlabs.io/blog/introducing-scribe-v2">https://elevenlabs.io/blog/introducing-scribe-v2</a>

Вы думали о добавлении другого поставщика услуг транскрипции речи в текст помимо OpenAI?

Have you thought about adding another speech-to-text transcription provider besides OpenAI?

I would like to be able to move the bar on the Windows app just like I am able to move the dot or bar in the browser add-on. To put it wherever I need it, maybe on the second monitor.

Customize the position of the floating bar.

I just tried out the beta version of Windows, and overall, I’m positively surprised. The system already makes a good impression.However, I would have liked more flexibility with the taskbar. Since I work with multiple screens, it would be ideal if I could freely move the taskbar between monitors. A feature that allows the taskbar to dynamically adapt to the desired screen would significantly improve usability.

Beta Version of Windows: First Impressions and a Wish for More Flexibility

Angelis 

Visual Studio Code Speech Extension example.it's really helpful.<img data-width="100%" data-align="left" data-featurebase-content-key="6749aff568c33a88d7b7547f/post/688ea7a8671961fb75f34a1c/01986d3d-dee3-7360-b1d7-f24ef7ad784f/b64u-MzA3MjU0MTc0LThmYzYwYTY2LTQ4MTgtNDJmNS04Mzc2LTMxYjEzMTBhY2U4Ni5wbmc.png" data-featurebase-content-filename="307254174-8fc60a66-4818-42f5-8376-31b1310ace86.png" src="https://6749aff568c33a88d7b7547f.featurebase-attachments.com/c/post/688ea7a8671961fb75f34a1c/01986d3d-dee3-7360-b1d7-f24ef7ad784f/b64u-MzA3MjU0MTc0LThmYzYwYTY2LTQ4MTgtNDJmNS04Mzc2LTMxYjEzMTBhY2U4Ni5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260221T090000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260221%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=70668d107f9b9334cff59b0cce7e790bd1a64608a9b4bb077b3d7738bd30c114">

Please incorporate a Speech Timeout feature.

mau karspesky

The update notification is shown after ending a recording, interrupting the transcription. Nothing is saved to history.

Update interrupts transcription

John

I think it's best to implement all the best features from Whisper Flow, add history, and other useful tools like formalizing writing and breaking it into paragraphs and so on. Perhaps include options for different speeds and precision, although everything is already quite good, fast, and faster than Whisper Flow. Maybe consider some dynamic pricing, like charging based on usage volume instead of a subscription. And let it show notifications, like whisper typing, about how much time is saved monthly, annually, or in total.

History +Wispr flow

HITECHDEM

With the advent of the end of Windows 10 support in October this year, many Windows 11 non-compliant PCs will be migrated to Linux distributions worldwide. Please make it a priority to develop the Blabby desktop version for GNU/Linux. It could be developed as a Flatpack with no need to make different versions for the various Linux distribution families.

Desktop version for Linux

David Ramos Barbón

I find that if I hold down the shortcut and maybe don't start to talk immediately or maybe pause after starting, it goofs it up and I get gibberish. I also have Wispr Flow and I don't experience anything like that with it, so it seems like something should be able to be done.

Can't handle pauses

tlwat

Folks, I love this tool, byt lately It is being quite annoying if I am honest … having it take what seems more than a minute to timeout when it lags … and that has been happening more often than I could just ignore it … for instance, now, perhaps 2 minutes after it started lagging, I chose to write the sentence myself at this point … and out of nowhere, as I am writing something completely different in another environment, it just pastes the content that I had dictated minutes ago …. and I also notice that for some reason it logged me out … things that are bearable when they happen like once a week, but kinda gets in the way of getting things done when they start to happen more than once a day (3rd time today already) … honestly I would prefere not to have it so slow of course, but if it is unavoidable as it seems to be, I wish I could at least set the timeout to be something shorter or just cancel with a button so at least it does not paste unappropriate content in random input boxes when I already forgot what I was trying to do. Really hoping this is fixable

Timeout too long in frequent lags

Are there any plans to add a rewriting feature to the Windows app in June 2025—the same one that was introduced for the browser extension?

Adding a rewriting feature

I have been using the desktop version. The Chrome version has always worked well.I have been finding on the desktop version that frequently Blabby is not inserting the dictated text. Instead, it is inserting the last thing that was on the Windows clipboard. If I check on the toolbar, I can see that the dictation has been captured on the most recent list. However, it's not inserting when I use it. This is happening in multiple programs including Word and Firefox.Often if I completely restart the program, it will start working again. I think the behavior starts when I copy something to the clipboard in Windows.

Completed

clipboard mixups.

chris phoon

Refactor technologies that currently require elevated privileges. This will allow the application to be launched without the need for administrator rights, eliminating the hassle of entering passwords or dealing with permission prompts. Improves convenience and provides a smoother, faster user experience

Remove Admin Privileges

We’re currently working on obtaining a code-signing certificate for our Windows app. Once completed, this will remove the “unknown publisher” warning and ensure a more seamless installation experience.Thank you for your patience, this is a priority for us, and we’ll update you as soon as it’s done! 🙌

現在、Windows アプリのコード署名証明書の取得に取り組んでいます。お待ちいただきありがとうございます。これは私たちにとって優先事項です！🙌

🛡️ コード・サイン

High Priority

🛡️ Code Signing

The day before yesterday a new model, GPT-5.2, was released. I’d really like to see this model in the list of options for custom mods.But if you do add it, please make sure to add the non-reasoning version, because it takes a very long time to think, and overall the cost of the reasoning model for you will be about 5–7 times higher than the non-reasoning one. That’s just not economically reasonable, and for the user, such long reasoning isn’t really desirable either.

Adding the GPT-5.2 model to custom modes

I was wondering if you’re planning to add GPT-5 as the default option for handling user mods in your program.I’ve been using GPT-5 myself for a while now, and it deals with complex prompts way more efficiently than GPT-4.1.

Adding the GPT-5 model for mods

I’m testing this on Windows, and I’ve run into an issue. The floating toolbar is no longer visible. All I can see is the tray icon. When I double-click the icon, it only opens the settings window. If I minimize the settings window, the icon just sits in the taskbar, and clicking it again only brings the settings back up. If I close the settings, the icon minimizes to the Windows tray, but re-opening it still only gives me the settings—never the actual floating toolbar with the dictation modes.This wasn’t the case when I first installed the software—the toolbar was available then—but after restarting my machine, it has disappeared.

Missing Floating Toolbar

Martin Devasia

I've attached an image showing a JavaScript problem occurring on my PC. Please fix this as soon as possible. Additionally, on some other computers I work on, the control space function doesn't work and doesn't switch the item or icon to listening mode. I've attached an image of this problem as well.<img data-width="100%" data-align="left" data-featurebase-content-key="6749aff568c33a88d7b7547f/post/686e139b85dcf45d9e1b29e0/0197edfc-8909-720f-a68b-679a144bea29/b64u-U2NyZWVuc2hvdCAyMDI1LTA3LTA5IDA5NTQzMi5wbmc.png" src="https://6749aff568c33a88d7b7547f.featurebase-attachments.com/c/post/686e139b85dcf45d9e1b29e0/0197edfc-8909-720f-a68b-679a144bea29/b64u-U2NyZWVuc2hvdCAyMDI1LTA3LTA5IDA5NTQzMi5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260221T090000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260221%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=00d10ffccb55b5506ab864bcd38f350c5921b816f85c9c67180c00766dbd290e" data-featurebase-content-filename="Screenshot 2025-07-09 095432.png">

JavaScript problem.

Naif Essa

I love the new minimal visuals, there is only one problem though. If I want to switch modes, there is basically no easy way to do that … so I had an idea … what if we could have an additional shortcut (customizable as well) to open the full bottom UI so we can change modes, go to settings, even paste some of the last transcriptions? All of that without changing the minimal visuals choice, it would show the full UI once and then gone … I thought maybe it would be less complex for it changes nothing in the UI, but idk, worth suggesting I guess =) thanks folks

Quick way to open options when using minimal visuals

I'm sorry, everyone, but I've been adding new notes and issues to the V.1.2.0 thread below, which has been marked as done. I should have started new threads for each issue, but everything is bundled together with this revision anyway.The only thing not related to version 1.2.0 is the topic of the microphone level, which I mistakenly included with my other comments; however, that was inappropriate.I deserve to be punished. —————————————————— The Blabby app automatically reduces my microphone level to about 75 out of 100, I think. I've tried everything I can in Windows, including adjusting privacy settings and app settings, as well as anything I could find in Windows itself, to maximize the volume.There is even a maximum level setting in Windows, which was at 75. I turned it up to 100, saved, applied, whatever it takes. And it seems to have gone back to 75 for some reason.At the 75 level, the dictation is not as accurate, so clearly the app is not recognizing or perceiving my voice correctly all the time.The small level bar that moves up and down as you speak is only reaching about 5 to 10% of its maximum potential.When I turn it up to 100 in the system settings, it seems to work much better. However, the maximum level keeps dropping to about 75 when I start to use Blabby . In fact, it just dropped from 100 to 81 while I'm dictating this message.When I went back to the Windows system settings, it had indeed been reset to 81. I have no idea why it changed to 81 instead of 75. Something is adjusting the maximum level, and it's setting it too low.

Blabby app automatically reduces my microphone level

There seem to be problems with this new version. Is it possible to revert to the previous version?Until now, I could dictate into almost every application I had open. However, now I cannot dictate into the application. The text is translated or transcribed, but I have to manually paste it from the translation app into the window where I need it using the retype option (right click on the three dots).The cursor is removed from the window I'm trying to dictate in. To insert the text, I have to click on that window again and use the retype function to enter the text that I've just dictated. So, the dictation function is working, but it isn't appearing where my cursor is. I have rebooted my computer. I have tried to restart every app to make sure that isn't a problem.The previous version of Blabby worked perfectly in this regard.