The ability to import a personal dictionary.

Rather than having to configure a personal dictionary word-by-word It would be nice to be able to import these as for example a CSV This might be particularly helpful for users who are migrating to Whisper AI from other voice-to-text systems

One off pricing with API key

Let users pay for a one-off license and use their own API keys

Support for custom API key integration?

Hey awesome team! 👋 First off, huge props for your incredible Voice-to-Text interface - it's absolutely fantastic! The UI/UX is just *chef's kiss* 🔥 Feature Request: Would it be possible to add support for custom API key integration? This would allow users to: 1. Use their own API keys from various providers - OpenAI - Other Speech-to-Text services - LLM services for text cleanup 2. Maintain your amazing two-step processing: - Initial voice recognition - Secondary LLM processing for formatting and cleanup The workflow would remain the same: 1. Voice input -> Raw text 2. Raw text -> Beautifully formatted output with proper punctuation But instead of using your backend services, it would utilize our own API keys/endpoints. Benefits: - Users can leverage existing API subscriptions - More flexibility in service choice - Cost control for high-volume users - Same great UI experience Would love to hear your thoughts on this! Is this something that could be considered for a future update? Thanks for your time! 🙏 #FeatureRequest #API #Integration #VoiceToText

Macstore app

If you can, I would like you to create a MacBook Pro App Store app so I can use it on other applications on my Mac, like Word document, WhatsApp, et cetera, et cetera, not having to be confined to be using it on Google Chrome.

Please add the openai api key feature

ios keyboard

Hey team! You’ve built a fantastic tool — I really enjoy using it. I’d love to suggest a feature: please consider creating a keyboard for iOS that works like the desktop Blabby version — where you can tap a single button (like a dot or mic icon) and instantly insert AI-transcribed text into any app. It would be amazing if this could happen directly inside the keyboard, without needing to switch to the Blabby app and back. There’s a similar product — SuperWhisper keyboard — but its UX is a bit clunky: you need to open the app first, then manually copy and paste the result. If you could build a native keyboard with GPT-4o speech recognition embedded — like Gboard but AI-powered — it would be a game-changer. I’d use it every day. Thanks for your great work!

The ability to customize your own prompt for the new rewriting feature.

This new feature, rewriting, that you guys just added is honestly super cool. There’s a ton of ways it could be put to use, but I wish there was an option to set up your own custom prompt. When you're writing, you end up dictating the same tasks over and over, when you could just put them in the prompt once and then use shorter cues to hit the mark, instead of repeating yourself every time you want something rewritten.

Speech to text prompt library you're welcome to use

Hey! Until you bring out a Linux app, I have to make do with my own very crude Whisper transcription client to fill the gap (there are lots of locally hosted Whisper models but I haven’t found one that uses the API and has direct text input yet). I use this for doing the kind of transcription I do with your tool, but also to capture texts that I then get formatted for use in common situations like creating emails, to-do lists, notes, etc. In the course of making these various prototypes, I've built up a small library of system prompts for what I call text transformation. I'm not sure if this is the official term, but I'm sure that you're familiar with the idea System prompts, which run the dictated text through an LLM to apply some basic transformations I mentioned before that I think it would be really amazing if there was something like a default library in Whisper AI that had the most common of these ready to go so that users could actually not just do direct transcription but also some reformatting or maybe as a secondary functionality. In case you ever do consider moving with the idea, I created an inventory of some of those system prompts earlier this week on GitHub, which you are more than welcome to use for this purpose: https://github.com/danielrosehill/Speech-To-Text-System-Prompt-Library

Snippets

Snippets creation and editing, like expanding small phases into something defined. like dictate - my email - returning yourmail@zzz.com would be great.

Some new features I would like to be added.

First, I would like the option to disable the dot in the end of each sentence. Secondly, I would like an option to say question mark and then a question mark will be added. And third, I would like the second feature to work on more things like enter, columns, and more.

Blabby Mobile App

I've been using Blabby for a while and it's awesome. I first started using it for ChatGPT, but now I just use all of my work apps inside Google Chrome and I get access. What I don't have, however, is the same level of functionality on my mobile. It would be so good to be able to use Blabby on the go. I'm an Android user, I don't know about iPhone, but the Android voice-to-text options are rubbish! Blabby for mobile please!

Microphone level tester

Just being a nuisance again and throwing in a few ideas! From using speech-to-text full-time for a few months now, I'm getting a good handle on what the occasional pitfalls are. One that I've noticed is if your microphone level is accidentally set too low, speech-to-text accuracy naturally declines a lot. Again, as a Linux user, I'm aware that there are peculiarities in this system that most users won't experience. But the one that I've encountered is whatever setting Zoom has that automatically changes the input levels persisting after leaving a Zoom call. Just about any time the Whisper performance seems to be lagging a bit, I check my microphone level and usually it's at something like 50%. I'm guessing that there will be a percentage of people using voice typing for the first time via this extension who will run into all these “rookie errors” and more. I don't know if a decibel meter could be integrated into the extension, but that’s one idea. Another is a warning that might display if the input volume is detected to be below a certain threshold. Something like “you’re too quite! Check your mic levels” (etc)

Mac up with Whisper Turbo?

I’d love to see a system-wide Mac app, especially one with a tier offering a one-time purchase for offline “ECO” mode. It could leverage the recently released Whisper Turbo model, which performs exceptionally well on Apple Silicon Macs, allowing for fast and efficient on-device transcription. I’ve been developing with Whisper Turbo, and I’m really impressed with its accuracy and efficiency!

Force the icon to appear if it is in the background or on another tab.

I've discovered that sometimes the little icon we use to activate dictation disappears. It's in the background somewhere; I just can't find it, and sometimes my keyboard shortcut is also not working. I think it is sometimes on another tab in my browser, lurking. It would be useful if the plug-in had something that could force it to the front of whatever tab you're on.

Separate shortcuts for starting and stopping dictation.

As we were discussing, for those using things like USB foot pedals, it might be advantageous to have separate configurable shortcut keys for starting and stopping dictation.

The option to choose different neural models for the rewriting feature.

Question: What model is currently set by default for the rewriting function? I’d really like it if, just like with transcription, we had the option to choose different models for rewriting. For example, as someone who’s been actively using GPT-4.1 and used GPT-4o for a long time, I can tell you that GPT-4.1 is way better than GPT-4o.

The return of the whitespace!

Just thought I would let you know, same thing as before, one character of trailing white space. Oddly it seemed to go away for a while. If it sheds any light on this - I trigger STT with a keyboard shortcut almost entirely (ie, I almost never click the little button). perhaps the keyboard shortcut is adding to the character string. Also: It's only a minor nuisance and far from a dealbreaker but I thought I'd keep up with their reporting

I'd love to hear more sound effects when transcription is activated or deactivated.

It would be great to add more sounds to activate and deactivate transcription, because when you activate transcription hundreds of times a day, these same sounds start to get pretty boring. Of course, this option is not super important, but overall it adds a pleasant feeling to using this great product.

Lagging Response

One irritating problem is that when I press an icon for a transcription, it takes a few seconds for my voice to be recorded. As a result, the first one to five words are completely ignored, which completely messes up the transcript. Is there some way of making the whole process faster? My XPS laptop has terrible function keys. Is anyone using a USB‑based external keypad? Will this speed up the responsiveness at the start of a transcription?

Option to turn off the special icon that pops up when you highlight text for the new rewriting feature.

It’d be great if there were an option in this new rewriting feature to turn the special icon on or off when you select text: Honestly, it’s kind of annoying as is. Personally, I’d much rather use hotkeys instead of having that icon pop up every single time.

🎉Early Beta Release of BlabbyAI Windows App is Here!

Hey Voice Typers! We’re excited to announce that the early beta version of BlabbyAIWindows app is finally here! Want to Try the Beta Now? Download the Beta Version Your enthusiasm and support have motivated us to bring this to you as soon as possible. However, there’s something important you should know before downloading: ⚠️About the Warning Message The app is now signed with a valid code-signing certificate. However, since it's a new release, Windows may still show a warning message. This is normal—Windows takes some time to fully trust new certificates. If you're comfortable proceeding, you can follow the steps below to bypass the warning. Here’s how to bypass the "unknown publisher" warning: If you encounter any unexpected behavior while using the app, don’t worry! You can easily close the app from the system tray to get things back to normal. We’d love to hear your feedback to make the app even better! Feel free to Request a feature / report a bug in the dedicated feedback portal. https://blabbyai.featurebase.app/ Thanks for being part of this journey! We can’t wait to hear what you think.

Automatic cutoff on silence

It would be useful to have an automatic cut-off in the event that the user is silent for perhaps 20 or 30 seconds. Occasionally it's easy to accidentally leave the recording open, which I presume is draining down the API credits and sending stuff for transcription for no reason.

I would like to be able to dictate punctuation such as open parentheses and close parentheses, as well as open quote and close quote.

Yearly pricing option

Hey, Sorry if this is something that I'm just not seeing, or maybe I signed up for the monthly option to test it out. It would be really nice to have the ability to pay for this yearly. For a lot of small business folks like me, even if there’s no monetary incentive to do so, it’s often easier to do yearly subs for good tools just to avoid the hassle of having to capture and account for the receipts every month, etc.

Anti-hallucination support, pause tolerance

Hey! I'm aware that the underlying engineering in getting all this to work is very complicated and that this would be really hard to achieve, but I said I would throw it out nevertheless. As you helpfully pointed out, ASR speech recognition has the amusing quirk of suffering from hallucinations much as large language models do generally. The manifestation in ASDR being that it will add nonsensical language like “thank you for watching” to the end of a transcription! I've really come to use speech to text as my daily typing method entirely thanks to your great app! So I still feel like I'm discovering how I use it as opposed to just text typing. One thing that I really like to do is to pause for thought while I'm in the middle of dictating. The problem is that if you leave long enough of a gap, you greatly increase the probability of hallucinations and at a certain point they're unavoidable. I don't really have any thoughts on what you could try to do to avoid this. If the pause detection is too aggressive then you run the risk of not capturing user text. But seeing as you've already made this amazing extension, I figure you know a lot more about the engineering than I can speculate about. Perhaps something like a user pause detection threshold setting would be helpful and allow those who dictate cleanly and those who like to pause for thought to choose a setting that best reflects their unique style.

Make standalone app work with Chrome extension.

It's quite often that you copy and paste stuff between different tabs, especially if you work with prompts. And it's quite often that you first want to dictate something and then paste a block of code or just some copied thing. And if you use the stand-alone Windows app, then your dictation will override the current content and the clipboard. In general, it would be nice to have an ability to add like an “exclusion” apps to windows app so Chrome extension could capture control+space hotkey first

For the keyboard shortcut on Chrome, when I assign control space, it is getting activated both control space and control shift space So effectively, it is taking up both the keyboard shortcut instead of taking just one

For the keyboard shortcut, when I assign control space, it is getting activated both control space and control shift space So effectively, it is taking up both the keyboard shortcut instead of taking just one

The option to disable the extension on specific websites isn’t working.

I’m trying to turn off the extension on sites where I don’t need it, so I’m not wasting my computer’s resources—especially since I have to open tons of tabs, like with Google Sheets. But for some reason, the extension just won’t deactivate on Google Sheets. No idea why. As you can see in the screenshot, the toggle is set to “off,” but that extension bar is still active in Google Sheets.

Allow to export and import of "Manage languages and their custom spellings" from one browser to other browser

Allow to export and import of "Manage languages and their custom spellings" from one browser to other browser

Desktop app for Linux.

It would be really great to have a desktop app for Linux as you are planning for Windows. Edited by BlabbyAI Dev: Hey guys, we’ve released a Linux beta version. This is the very first version so expect some rough edges. Dictation should work as expected but other parts may still be unusable. https://www.blabby.ai/linux-speech-to-text

Please let us get rid of any bars bubbles and all that. Just make it work on a shortcut and that's it. Seriously who needs any other options? And if they need, just make it optional to have any bars, etc.

Especially now, the bar on the bottom made me almost immediately uninstall this, but I really enjoy the plugin overall.

Would you like a sticky bottom toolbar?

A lot of people have trouble with the dot toolbar disappearing sometimes (we’ll fix that!) We’re thinking about a new design, a toolbar that sticks to the bottom of the browser tab and appears only when you need it. It will include all the modes in one place and have shortcuts for each mode to make things faster and easier.

Plans specifically for high volume users

I understand how and why offering things like unlimited lifetime deals might be financially unviable given that you have to pay the API costs. However, as someone who has begun using your extension literally all the time, it would be fantastic to be able to have a “set-it-and-forget-it” type subscription rather than having to keep an eye on a credit availability all the time. I think that for business users this could be offered as a more expensive tier that is perhaps unlimited but still has to be funded monthly. I won't to suggest increasing the price of a service that I love, but equally I'd love to have access to a tier that I could expense for client work. If there were such a high volume tier, I would certainly subscribe.

Demo of bug when logged into two accounts.

Sharing a screen recording with a demonstration of the weird behavior I'm experiencing when logged into two different Chrome profiles, each with Whisper AI as an extension. The problematic behavior seems to be the shortcut behavior on the second extension and it not recognizing when tabs are changed I seem to have been able to isolate it to when both Chrome profiles are running.

Blabby desktop app for Linux

With the end of support for Windows 10, many PCs are being migrated to Linux worldwide. Please make a package (e.g., a Flatpak) of the desktop Blabby application for Linux distributions. Edited by BlabbyAI Dev: Hey guys, we’ve released a Linux beta version. This is the very first version so expect some rough edges. Dictation should work as expected but other parts may still be unusable. https://www.blabby.ai/linux-speech-to-text

Adding the GPT-5 model

This week, OpenAI dropped their new GPT-5 model. Price-wise, it's about the same as GPT-4.0 and GPT-4.1. Are you planning to add this model to your extension?

Ability to move control panel around Chrome

Hello there. I like the new updates you all made to the Chrome browser extension. However, I'm having an issue where it is in the center bottom portion of my Chrome window, which blocks access to some things that I have to type. Can you please make it so I can move the control panel around like we used to before it was updated? Thank you for your time and consideration, Sean.

One issue with the new button UI - it gets in the way quite a lot!

two writtings

When I speak, it writes what I said twice instead of once, It only happens to me when I use the GPT-4O and GPT-4O Mini models. When I use Whisper, it doesn’t happen. But since Whisper doesn’t translate very well, I prefer to use the other models