Dictate Keyboard (Whisper AI)

DevEmperor

About this app

Dictate is a simple yet powerful keyboard, which converts spoken language into text. It uses an extremely powerful speech recognition AI in the background and therefore supports all common national languages. What's more, you don't have to dictate punctuation because Whisper adds it itself. You can even sing in text and it will be recognized correctly.

Other features include:
- custom rewording instructions (translation, summarizing, style-changing, ...) using GPT-5 (and many other models) 💡
- switching between different transcriptions models (Whisper, GPT-4o-transcribe, ...) and providers (OpenAI, Groq or your own transcription server) 🔄
- transcription of voice and audio or video files 📄
- recording using phone or Bluetooth microphone 🎧
- setting a system prompt to guide the style of the speech recognition and rewording ✏️
- dark-mode, light-mode and custom theme settings ✨
- direct input, without the typing animation ⏱️
- quick switching to the standard keyboard ⌨️
- haptic feedback 📳
- custom API server and proxy support 🛠️
- simple use and setup process 💪

For the app to be fully functional, every user must create an API key with OpenAI or Groq when setting it up for the first time. This incurs very low fees for each transcription (usually a few cents per month). There is a detailed explanation of this during setup.

Dictate is completely open source, the source code is available on GitHub.
https://github.com/DevEmperor/Dictate

If you have any bugs or suggestions for improvement, just write me an e-mail or open an issue on GitHub.

If you like Dictate, I would really appreciate a donation via PayPal. You can find my PayPal-Link on my GitHub page. 😇

Have fun with Dictate! 😊

Ratings and reviews

like many, I too want a physical keyboard within the app. my phone keeps defaulting back to gboard and it's hard to get to dictate. I haven't been able to get a downloaded audio file to transcribe yet, even though I long press nothing happens, ui isn't as intuitive as dev want you to believe. help could be more helpful, how about adding some short screen recordings to show us exactly how to use each feature? dev responds to 90% reviews but can't bother to put in a keyboard? hmmm...

I have had it an hour. I'm using the free API key from Grok. So, from my experience, it's way better than anything that comes with the phone. I'm using a Galaxy Note 20. And it's fantastic. And if you're having problems working with Gemini or any LLM models that have tricky dictate buttons, it's great. And it also looks like you can transcript files. Like I said, I've been only using it for an hour. But from what I can tell, it's well worth the money. And hoping this grows into a great tool.

This is a really cool indie app that perfectly transcribes voice notes. I use it to type text using my voice on the go, to transcribe voice notes and brainstorms, and I really love it. It uses the OpenAI API key and doesn't ask for in-app purchases, so it's really cheap and reliable. I really love it. PS: I have typed this review using dictate and didn't edit it.

What’s new

Dictate 2.10.0

- You can now record using the microphone of your headphones. So if you want to walk around more freely, this will help you a lot. 🎧
- If you tap, hold and swip to the left on the delete button, you can now select whole words for faster but still precise deletion. 🗑️
- You can now set a custom system prompt for rewording models in the settings. 💡