A minimal speech-to-text widget that works locally on your Mac. Activate with a shortcut, speak anywhere you'd normally type, and watch your words appear instantly. Perfect for AI chats, emails, and any text field.
Testing out your app. When I open it with the shortcut keys, it shows up, I speak into the mic and all it always types is Thank you. I gave it permission with Privacy settings
Hi @karlclement , thank you for trying out Harker. That’s a common Whisper hallucination, caused by its training data and how it interprets silence, background noise, or clicks. Can you confirm that your microphone is properly connected and working? Do you see the “Harker line” moving in sync with your voice while you're speaking?
Report
I purchased Hacker and gave it a try. It works well for the English language, but I would say that multilingual support is lacking. Whenever I speak in Slovene (one of the Slavic languages), it always detects it as Russian. Thus, language detection is not functioning effectively. It would be better to have a configuration option that allows users to choose which languages are enabled.
Hey @mitjakukovec , thanks for trying out Harker Have you tried picking a larger multi-language model from the settings? That usually is enough to solve the precision transcription issues for less common languages as well.
Please if you do, let me know how it goes
Report
I am an early supporter of Harker, and it has been excellent for English right out of the box.
In addition to English, I want to use it with Slovene, my native Slavic language. When I speak to Harker in Slovene, it always transcribes the detected speech in Cyrillic, which is not the Slovenian alphabet. I can somewhat mitigate this issue by first informing the model in English to recognize and transcribe the next speech as Slovene. However, this also includes my guiding words in the transcription.
It would be very helpful to have an option to pre-prompt the AI model in its configuration settings. This way, the AI could be directed in advance on how to handle different situations.
Replies
Squire AI
Testing out your app. When I open it with the shortcut keys, it shows up, I speak into the mic and all it always types is Thank you. I gave it permission with Privacy settings
Harker
Hi @karlclement , thank you for trying out Harker.
That’s a common Whisper hallucination, caused by its training data and how it interprets silence, background noise, or clicks.
Can you confirm that your microphone is properly connected and working? Do you see the “Harker line” moving in sync with your voice while you're speaking?
I purchased Hacker and gave it a try. It works well for the English language, but I would say that multilingual support is lacking. Whenever I speak in Slovene (one of the Slavic languages), it always detects it as Russian. Thus, language detection is not functioning effectively. It would be better to have a configuration option that allows users to choose which languages are enabled.
Harker
Hey @mitjakukovec , thanks for trying out Harker
Have you tried picking a larger multi-language model from the settings? That usually is enough to solve the precision transcription issues for less common languages as well.
Please if you do, let me know how it goes
I am an early supporter of Harker, and it has been excellent for English right out of the box.
In addition to English, I want to use it with Slovene, my native Slavic language. When I speak to Harker in Slovene, it always transcribes the detected speech in Cyrillic, which is not the Slovenian alphabet. I can somewhat mitigate this issue by first informing the model in English to recognize and transcribe the next speech as Slovene. However, this also includes my guiding words in the transcription.
It would be very helpful to have an option to pre-prompt the AI model in its configuration settings. This way, the AI could be directed in advance on how to handle different situations.