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.
Hey Product Hunt community! 👋
I'm thrilled to share Harker with you today. As someone who spends way too much time typing, I got frustrated with how slow my fingers were compared to my thoughts. And with all the AI conversations we're having these days, we're typing more than ever!
That's when I realized most speech-to-text tools send your data to the cloud, or interrupt your workflow.
Harker is different. Your voice never leaves your Mac, it launches instantly with a keyboard shortcut, and works in any text field. The interface stays hidden until you need it, then appears with a clean, minimal UI. Whether you're writing emails, chatting with AI, or taking notes, just hit the shortcut, speak, and your words appear exactly where you need them.
I initially developed Harker for myself, I've been using it for months now and honestly can't imagine going back to typing everything.
Would love to hear what you think and answer any questions! What would you use voice-to-text for in your daily workflow?
Thanks for checking it out!
The problem I notice with local AI / ML applications is they are processing pretty slow. Would be nice to see some benchmarks (not sure how to visualize that when benchmarking audio tho lol).
Nice launch tho, super nice product, was just recently looking for alternatives on subscription-based apps like Wispr Flow.
@mxmzb Totally fair. Local AI can feel slow depending on the setup and model size. Harker gives you the option to download and choose the model that best fits your machine, so you can get the right tradeoff between speed and accuracy.
For English-only models, even the smaller ones are surprisingly precise and very fast on M1 or M2. With no loading screens or cloud roundtrips.
Running everything locally also means no server costs, which lets me offer Harker as a one-time purchase. No subscriptions, the app is yours to use.
Benchmarking audio is tricky to show, but I’m thinking about adding a simple demo or side-by-side soon. Thanks for checking it out, and yes, it’s built as a simpler, privacy focused, and no-subscription alternative to more complex tools like Wispr Flow
Have you thought about benchmarking this for accuracy against the built-in macOS voice recognition? That’s what I use today, and it’s built in and free, so that’s your basic competition.
Hey@jasonrdunn , very good point, thank you. I actually developed Harker first for myself exactly as a substitution for the Mac built-in speech-to-text. I wanted something running locally and that can be calles with a simple shortcut, and that automatically paste the output in the selected textfield.
It depends a bit on what is the language you want to transcribe and on which model you pick, but in general, being based on whisper, the accuracy is way higher compared to the Mac built-in tool.
If you end up trying, please let me know how it goes. Thanks
Thank you for introducing this minimal speech-to-text widget! 🎙️✨ It’s awesome to have a local solution on Mac that lets me dictate anywhere I’d normally type. 🚀 Whether it’s for AI chats, emails, or any text field, this will definitely boost productivity and make typing so much easier. 💻🗣️ Love the instant transcription and shortcut activation! Keep up the great work! 👏😊
@anthony_sanna1 I'm sorry but Harker works on M-series processors only. I tried packaging the app for older Macs, but the local transcription is a bit too demanding for old hardwares, and it takes too long to make it worth it unfortunately.
Hi @vladimir_vashnev , Harker is based on whisper, that is the same "engine" many speech-to-text software use nowadays, at least as a starting point. The difference is that Harker runs locally, and you can pick exactly the model you want to use from the settings. So the quality/speed depends mostly on the model you pick, and the hardwere you have. But it's fairly simple to adjust the settings to your needs.
If you end up trying, please let me know how it goes. Thanks
@vladimir_vashnev@mnlcpcI'm currently using Wispr Flow, and I love it, but it's a little expensive I'm not that keen on every word I say being sent to foreign datacenters. Do you offer a money back guarantee if I buy Harker and it doesn't meet my needs?
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?
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.
Replies
Harker
The problem I notice with local AI / ML applications is they are processing pretty slow. Would be nice to see some benchmarks (not sure how to visualize that when benchmarking audio tho lol).
Nice launch tho, super nice product, was just recently looking for alternatives on subscription-based apps like Wispr Flow.
Harker
@mxmzb Totally fair. Local AI can feel slow depending on the setup and model size. Harker gives you the option to download and choose the model that best fits your machine, so you can get the right tradeoff between speed and accuracy.
For English-only models, even the smaller ones are surprisingly precise and very fast on M1 or M2. With no loading screens or cloud roundtrips.
Running everything locally also means no server costs, which lets me offer Harker as a one-time purchase.
No subscriptions, the app is yours to use.
Benchmarking audio is tricky to show, but I’m thinking about adding a simple demo or side-by-side soon.
Thanks for checking it out, and yes, it’s built as a simpler, privacy focused, and no-subscription alternative to more complex tools like Wispr Flow
@mxmzb @mnlcpc you might want to take down your PH page with the launch discount code if you're not going to honor it.... PH50OFF is EXPIRED.
Harker
Hi @jep9 , sure the code is expired now, but was active DURING the launch :)
But if you want to try Harker, please send me a message
Have you thought about benchmarking this for accuracy against the built-in macOS voice recognition? That’s what I use today, and it’s built in and free, so that’s your basic competition.
Harker
Hey@jasonrdunn , very good point, thank you.
I actually developed Harker first for myself exactly as a substitution for the Mac built-in speech-to-text. I wanted something running locally and that can be calles with a simple shortcut, and that automatically paste the output in the selected textfield.
It depends a bit on what is the language you want to transcribe and on which model you pick, but in general, being based on whisper, the accuracy is way higher compared to the Mac built-in tool.
If you end up trying, please let me know how it goes. Thanks
Pokecut
Thank you for introducing this minimal speech-to-text widget! 🎙️✨ It’s awesome to have a local solution on Mac that lets me dictate anywhere I’d normally type. 🚀 Whether it’s for AI chats, emails, or any text field, this will definitely boost productivity and make typing so much easier. 💻🗣️ Love the instant transcription and shortcut activation! Keep up the great work! 👏😊
So, you are using local/offline SLM?
Harker
@manu_goel2 yes, the speech to text model is embedded in the app.
@mnlcpc love it ... that's tech put to right use
Harker
Thank you @manu_goel2 , appreciate it
Will it run on any Mac OS? I have an old 2008 Macbook running 10.4 and a newer iMac 2020 running Monterey 12.7.6.
Harker
@anthony_sanna1 I'm sorry but Harker works on M-series processors only. I tried packaging the app for older Macs, but the local transcription is a bit too demanding for old hardwares, and it takes too long to make it worth it unfortunately.
How do I test the quality/speed and supported languages of the app before buying?
Harker
Hi @vladimir_vashnev ,
Harker is based on whisper, that is the same "engine" many speech-to-text software use nowadays, at least as a starting point.
The difference is that Harker runs locally, and you can pick exactly the model you want to use from the settings.
So the quality/speed depends mostly on the model you pick, and the hardwere you have. But it's fairly simple to adjust the settings to your needs.
If you end up trying, please let me know how it goes. Thanks
@vladimir_vashnev @mnlcpcI'm currently using Wispr Flow, and I love it, but it's a little expensive I'm not that keen on every word I say being sent to foreign datacenters. Do you offer a money back guarantee if I buy Harker and it doesn't meet my needs?
Harker
Yes @shane_doherty . Just get in touch with me in case. I'd love to hear your feedback, especially in comparison with your experience with Wispr Flow
@mnlcpc Thanks!
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