Hi there 👋,
I’m excited to share a project I’ve been working on over the past few months!
My primary goal is to create a service that will be beneficial for people. The app is completely free and does not require registration. Please share your thoughts on this idea, and suggest any new features you think I should implement!
Exciting Features:
- Speak to Write: with this feature, you can speak your thoughts or information and the tool will transcribe it into text. The best part? You can then forward the transcribed text to any application with just one click. For example, you could set up an automatic export feature for your Notion account.
- Audio to Action Plan: the service can transform a received audio message into a structured list of elements or bullet points. This feature is especially useful for outlining an action plan or item list.
- Speak in any Language: you can dictate an audio message in your native language, and the service will translate it into any other language, maintaining high translation quality—significantly better than Google Translate.
- Meeting Transcripts & Summaries: the service is perfect for converting recorded audio from meetings into text and generating concise summaries. It supports the upload of users’ files.
Thank you for taking the ti me to check it out. I look forward to hearing your feedback. You can access the service by visiting this link: https://audionotes.ai 🙏
That sounds interesting
Isnt this basically otter ai app?
What do you think are the features I need to add to the service?
I have quite a long backlog that needs to be done. But it’s hard for me to prioritize them.
For now, I’m thinking of adding these features:
• Create native app for iPhone and Android (now I use PWA)
• Option to merge several notes into one
• Ability to add tags to each note for easy searchI tried the program and I had an error pop up. It disappeared too fast for me to read it. Is there a better way to list the error log? The recording processing was then caught in a loop displaying 0,99,0,99 and quickly flashed between those numbers. Otherwise, it seems like a really neat program. I was using a Samsung galaxy z3 if that helps
Thank you for trying!
I don’t remember when the message about the error is disappearing; all these types of errors are static. Please try one more time to test the service.
Can this help make MOMs using a recorded 2 hour video file?
Just so the readers of this thread know, there are several “Speak to Write” apps available across different platforms. Keep in mind that the popularity and availability of apps can change, and new apps may have been released since then. Here are some examples:
Google Docs Voice Typing:
Platform: Web-based (Google Docs)
Google Docs offers a Voice Typing feature that allows users to dictate and have their speech converted into text.
Microsoft Dictate:
Platform: Microsoft Office (Word, Outlook, etc.)
Dictate is a Microsoft Office add-in that enables users to speak and have their words transcribed into written text in various Office applications.
Dragon NaturallySpeaking:
Platform: Windows
Dragon NaturallySpeaking, now known as Dragon Professional Individual, is a popular speech recognition software for Windows.
Apple Dictation:
Platform: macOS and iOS
Apple devices, including Mac computers and iPhones/iPads, come with built-in Dictation features that allow users to speak and convert their speech into text.
Otter.ai:
Platform: Web, iOS, Android
Otter.ai is a note-taking app that utilizes speech-to-text technology. It’s particularly useful for transcribing meetings, interviews, and conversations.
Google Keyboard (Gboard):
Platform: Android, iOS
Gboard, Google’s keyboard app for Android and iOS, includes a voice typing feature that allows users to dictate text.
Speechnotes:
Platform: Web, Android, iOS
Speechnotes is a speech-to-text notepad app that allows users to dictate and transcribe their spoken words.
iSpeech Dictation:
Platform: Web, Android, iOS
iSpeech Dictation is a mobile app that converts spoken words into text and supports multiple languages.
Windows Speech Recognition:
Platform: Windows
Windows operating systems come with built-in speech recognition features that allow users to control their computers and dictate text.
Dictation.io:
Platform: Web
Dictation.io is a web-based application that provides speech-to-text functionality. Users can speak into their microphone, and the app transcribes the speech into text.Good call on your part, this is especially useful information to have taking the practicality of this tool into account.
At the same time, I think this thing still has a chance to shine primarily due to the accuracy of a lot of these services and how they function. Would be surprising if it could beat Google at such a feature but from my own experience the voice typing in Google Docs isn’t very effective, a lot of the time it’s stilted or slow and ultimately makes you want to type instead of speak.
I’m not sure what improvements have to be made performance wise or how to increase the accuracy and speed of such a thing, but the room is still there for an idea.
I need English audio to Bangla text. But Bangla is not available.
There was a project on Kickstarter a few months ago that reminds me of this. I think it was called the Plaud Note? It was basically a mini recording device that could transcribe and summarize meetings or lectures. I thought it was a cool idea, maybe look into them and see what they’re offering. I’ll add a link if I can find it again.
Great
🙏
So, this is basically a combination of Google Translate/Live Transcribe, piped through ChatGPT? How is it better?
Probably uses Whisper.
Loving the “Speak to Write” feature - so handy for dumping my brain directly into text. And that “Audio to Action Plan” is a productivity dream! 💡 Also, the multilingual magic? Bravo! Translation quality beats Google Translate hands down.
Excited to see where you take this—cheers to making our lives easier, one audio note at a time!
link is broken.
Sounds nice so far, i will test it 👌🏻
My thoughts:
Positive ->- Great Idea
- Nice clean UI
- Note dictation is good
Negatives ->
- Recording freezes while talking
- Summary changes the actual meaning of the note
- UX is very wonky: uploading files or settings shouldn’t be on top menu. Plus need more focus on other features/functions
Curious: what does this do that the text to speech in something like word does not? And what exactly does the AI add to the process that makes it necessary?
Curious - did you use OpenAI or a different api?