Feedback
Roadmap

Have something to say?

Tell us how we could make the product more useful to you.

Pinned

In Progress

🎉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 Since this is an early beta release, we’re still in the process of obtaining a code-signing certificate. This means that when you download the app, your Windows machine might display a warning about an “unknown publisher.” Don’t worry, this is normal for unsigned apps and doesn’t mean the app is unsafe. If you’re comfortable trying the beta now, you can follow the steps below to bypass the warning. If you’d prefer to wait until the app is fully code-signed, that’s completely fine too! We’ll notify you again when it’s ready. Subscribe here 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.

BlabbyAI Dev 2 months ago

1

In Progress

Proposal: Switching from Whisper to the new GPT-4o-transcribe model

As an active user of your Chrome extension, I'd like to suggest an improvement that would significantly enhance transcription accuracy. 1. Current issue I've been using the extension for audio transcription for over a month. When working with Russian language, numerous errors occur. This requires extensive manual corrections, reducing work efficiency. 2. Solution: Transition to GPT-4o-transcribe OpenAI has released a new transcription model that substantially outperforms the current Whisper: https://openai.com/index/introducing-our-next-generation-audio-models/ Key advantages: Significantly improved accuracy (reduced Word Error Rate), tested on more than 100 languages Better recognition of accents and regional speech patterns Increased resilience to background noise during recording Adaptation to varying speech speeds Reduction of incorrect interpretations for complex words Better context understanding and recognition of specific terminology 3. Alternative solution: If the full GPT-4o-transcribe version proves too expensive, you could implement gpt-4o-mini-transcribe. Even this mini version significantly outperforms the current Whisper model in terms of accuracy and reliability. 4. Simple integration This enhancement requires minimal effort — simply changing the model name used in the API request.

Web 3 days ago

1

Upload content while dictatiing

The system is excellent and performs exactly as intended, with impressive text conversion and explanation capabilities. The mods are also working great, providing clear explanations. However, I would suggest adding a feature that allows users to upload content (such as code snippets or text) before interacting with specific mods, like translation or coding mods. This would enhance functionality, especially when working with code where we need to submit it first before requesting modifications. Overall, I'm very satisfied with the well-organized system, reasonable pricing, and will continue using it long-term.

Naif Essa 17 days ago

2

Rollover of unused transcription minutes to the next month

I've got a question. Do you have it set up so that when you renew your subscription next month, any unused transcription minutes from the previous month roll over and get added to the new minutes you pay for this month? In other words, do you carry over unused limits from past months to the next month or not? If not, that would be a fascinating feature to add.

Web 27 days ago

1

Planned

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)

danielrosehill About 1 month ago

1

Support for Deepgram, other STT APIs

Whisper AI is one of those rare technologies that has almost exhausted my ability to generate feature requests because it pretty much just works, which is a great achievement! But in the spirit of sharing ideas and because it's something that I thought about in the early days of testing this stuff out, I wanted to put in the idea that supporting a variety of SGT Cloud APIs might be useful for users. I'm guessing that it would be more hassle than it's worth and it's not really in sync with the Whisper brand (!), but DeepGram's APIs are good, and there are a few others that are useful too. One use case that I would highlight is that I believe a couple of these more niche platforms have explicit support for speaker accents in their API architecture. Users who have very pronounced or more unusual accents might find that the recognition is enhanced with these without having to go through the trouble of fine-tuning a model. Some other providers I’ve come across: Gladia, Speechmatics. As ASR is really heating up, I imagine the list will just keep growing.

danielrosehill About 1 month ago

Can I increase the number of minutes for transcription on the pro plan or buy minutes extra?

Is there any way to increase the number of transcription minutes on the “PRO” plan, or maybe add more plan options? In my case, I constantly use complex prompts for transcription, utilizing my custom modes, and this eats up a massive amount of tokens. I feel like the current transcription limits on the PRO plan definitely won't be enough for me for a month. Or is there any option to purchase additional minutes?

Web About 1 month ago

1

Planned

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!

Theo About 1 month ago

Planned

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.

Thomas Dahl 2 months ago

4

Planned

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!

Julian Gillespie 2 months ago

4

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

Nod Ulus 2 months ago

3

In Progress

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.

danielrosehill 2 months ago

2