[HN Gopher] Handy - Free open source speech-to-text app
       ___________________________________________________________________
        
       Handy - Free open source speech-to-text app
        
       Author : tin7in
       Score  : 196 points
       Date   : 2026-01-15 05:23 UTC (17 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | dotancohen wrote:
       | Looks interesting. Why does it need a GUI at all?
        
         | kristianp wrote:
         | So more people can use it?
        
         | Barbing wrote:
         | I hear a CLI request? Tons of CLI speech-to-text tools by the
         | way, really glad to see this. Excellent competitors
         | (Superwhisper, MacWhisper, etc.) are closed/paid.
        
         | tin7in wrote:
         | As an alternative to Wisprflow, Superwhisper and so on. It
         | works really well compared to the commercial competitors but
         | with a local model.
        
         | satvikpendem wrote:
         | Because local AI models run well on a GPU, better than on a CPU
        
         | unwind wrote:
         | Ah, that was a typo: you meant "GPU" (Graphics Processing Unit,
         | not "GUI" which of course is Graphical User Interface) since
         | that is listed in the system requirements. Explained implicitly
         | by an existing comment, thanks!
        
         | sipjca wrote:
         | It doesn't! Just makes it more accessible to more people I
         | feel. There's a cli version for Mac which I wrote first handy-
         | cli
        
       | Jack5500 wrote:
       | The Parakeet V3 model is really great!
        
       | jborichevskiy wrote:
       | Big Handy fan!
        
       | frankdilo wrote:
       | This looks great! What's missing for me to switch from something
       | like Wispr Flow is the ability to provide a dictionary for
       | commonly mistaken words (name of your company, people, code
       | libraries).
        
         | tin7in wrote:
         | It has something called "Custom Words" which might be what you
         | are describing. Haven't tested this feature yet properly.
        
         | jauntywundrkind wrote:
         | I dig that some models have an ability to say how sure they are
         | of words. Manually entering a bunch of special words is ok, but
         | I want to be able to review the output and see what words the
         | model was less sure of, so I can go find out what I might need
         | to add.
        
         | sipjca wrote:
         | There's a PR for this which will be pulled in soon enough, I
         | can kick off a build of the PR if you want to download a pre
         | release version
        
           | sipjca wrote:
           | Okay so it's more directly text replacements
           | 
           | https://github.com/cjpais/Handy/actions/runs/21025848728
           | 
           | There is also LLM post processing which can do this, and the
           | built in dictionary feature
        
       | vladstudio wrote:
       | Use it daily. Looks and works great.
        
       | chainmail2029 wrote:
       | There's a slightly awkward naming overlap with an existing
       | product.
        
         | unwind wrote:
         | Which one? I did a quick search but that didn't turn up
         | anything so perhaps it's a partial word overlap or something.
         | 
         | I did find the projects "user-facing" home page [1] which was
         | nice. I found it rather hard to find a link from that to the
         | code on GitHub, which was surprising.
         | 
         | [1]: https://handy.computer/
        
           | DomB wrote:
           | It's the German word for smart phone / mobile phone
        
           | zavec wrote:
           | There's also a sex toy
        
         | ensocode wrote:
         | This is a slightly German-centric comment.
        
       | PhilippGille wrote:
       | Has anyone compared this with https://github.com/HeroTools/open-
       | whispr already? From the description they seem very similar.
       | 
       | Handy first release was June 2025, OpenWhispr a month later.
       | Handy has ~11k GitHub stars, OpenWhispr has ~730.
        
         | kuatroka wrote:
         | I did have tried, but the ease of installing handy as just a
         | macOS app is so much simpler than needing to constantly run in
         | npm commands. I think at the time when I was checking it, which
         | was a couple of months ago they did not have the parakeet
         | model, which is a non-whisper model, so I had decided against
         | it. If I remember correctly, the UI was also not the smoothest.
         | 
         | Handy's ui is so clean and minimalistic that you always know
         | what to do or where to go. Yes, it lacks in some advanced
         | features, but honestly, I've been using it for two months now
         | and I've never looked back or searched for any other STT app.
        
           | ranguna wrote:
           | The OP asked if someone compared both, which usually means
           | actually trying both and not just installing one and skimming
           | through the other's README file. So, in summary, you didn't
           | try both and didn't answer the OP.
        
       | dumbmrblah wrote:
       | I just set this up today. I had Whispering app set up on my
       | Windows computer, but it really wasn't working well on my Ubuntu
       | computer that I just set up. I found Handy randomly. It was the
       | last app I needed to go Linux full-time. Thank you!
        
       | llarsson wrote:
       | A question because I'm not using speech-to-text, but find it
       | intriguing (especially since it's now possible to do locally and
       | for free).
       | 
       | How have your computing habits changed as a result of having
       | this? When do you typically use this instead of typing on the
       | keyboard?
        
         | tin7in wrote:
         | I use it all the time with coding agents, especially if I'm
         | running multiple terminals. It's way faster to talk than type.
         | The only problem is that it looks awkward if there are others
         | around.
        
           | johnisgood wrote:
           | Interesting. I can think and type faster, but not talk. I am
           | not much of a talker.
        
             | stavros wrote:
             | Same, whenever I try to dictate something I always umm and
             | ahhh and go back a bunch of times, and it's faster to just
             | type. I guess it's just a matter of practice, and I'm fine
             | when I'm talking to other people, it's only dictation I'm
             | having trouble with.
        
         | noneofyour wrote:
         | Part of my job is to give feedback to people using Word
         | Comments. Using STT, it's been a breeze. The time saving really
         | is great. Thing is, I only do this when working at home with no
         | one around. So really only when WFH.
        
       | blutoot wrote:
       | Crashes on Tahoe 26.3 Betq 1 :(
        
         | sipjca wrote:
         | Please send me a crash log!
        
       | Dnguyen wrote:
       | Would be nice if the output can be piped directly into Claude
       | Code.
        
       | mrroryflint wrote:
       | On a M4 Macbook Air, there was enough lag to make it unusable for
       | me. I hit the shortcut and start speaking but there was always a
       | 1-2sec delay before it would actually start transcribing even if
       | the icon was displayed.
        
         | jborichevskiy wrote:
         | Curious if you were using AirPods or other Bluetooth headphones
         | for this?
         | 
         | If so, there should be "keep microphone on" or similar setting
         | in the config that may help with this, alternatively, I set my
         | microphone to my MacBook mic so that my headphones aren't
         | involved at all and there is much less latency on activation
        
           | mrroryflint wrote:
           | Airpods Max (is that the name?) - the big ones.
        
         | sipjca wrote:
         | What microphone are you using?
        
           | mrroryflint wrote:
           | Airpods Max (is that the name?) - the big ones.
        
         | kuatroka wrote:
         | Yes, I've got the same situation too. I kind of learned to wait
         | for one or two seconds before talking. I am using it with the
         | AirPods, so maybe it's indeed the Bluetooth thing.
        
       | blutoot wrote:
       | I have dystonia which often stiffens my arms in a way that makes
       | it impossible for me to type on a keyboard. TTS apps like
       | SuperWhisper have proven to be very helpful for me in such
       | situations. I am hoping to get a similar experience out of
       | "Handy" (very apt maming from my perspective).
       | 
       | I do, however, wonder if there is a way all these TTS tools can
       | get to the next level. The generated text should not be just a
       | verbatim copy of what I just said, but depending on the context,
       | it should elaborate. For example, if my cursor is actively inside
       | an editor/IDE with some code, my coding-related verbal prompts
       | should actually generate the right/desired code in that IDE.
       | 
       | Perhaps this is a bit of combining TTS with computer-use.
        
         | hasperdi wrote:
         | What you said is possible by feeding the output of speech-to-
         | text tools into an LLM. You can prompt the LLM to make sense of
         | what you're trying to achieve and create sets of actions. With
         | a CLI it's trivial, you can have your verbal command translated
         | into working shell commands. With a GUI it's slightly more
         | complicated because the LLM agent needs to know what you see on
         | the screen, etc.
         | 
         | That CLI bit I mentioned earlier is already possible. For
         | instance, on macOS there's an app called MacWhisper that can
         | send dictation output to an OpenAI-compatible endpoint.
        
           | sipjca wrote:
           | Handy can post process with LLMs too! It's just currently
           | hidden behind a debug menu as an alpha feature
           | (ctrl/cmd+shift+d)
        
             | sanex wrote:
             | I was just thinking about building something like this,
             | looks like you beat me to the punch, I will have to try it
             | out. I'm curious if you're able to give commands just as
             | well as some wording you want cleaned up. I could see a
             | model being confused between editting the command input
             | into text to be inserted and responding to the command.
             | Sorry if that's unclear, might be better if I just try it.
        
         | sipjca wrote:
         | I totally agree with you and largely what you're describing is
         | one of the reasons I made Handy open source. I really want to
         | see something like this and see someone go experiment with
         | making it happen. I did hear some people playing with using
         | some small local models (moondream, qwen) to get some more
         | context of the computer itself
         | 
         | I initially had a ton of keyboard shortcuts in handy for myself
         | when I had a broken finger and was in a cast. It let me play
         | with the simplest form of this contextual thing, as shortcuts
         | could effectively be mapped to certain apps with very clear
         | uses cases
        
         | eddyg wrote:
         | There's lots of existing work on "coding by voice" _long_
         | before LLMs were a thing. For example (from 2013):
         | http://xahlee.info/emacs/emacs/using_voice_to_code.html and the
         | associated HN discussion ("Using Voice to Code Faster than
         | Keyboard"): https://news.ycombinator.com/item?id=6203805
         | 
         | There's also more recent-ish research, like
         | https://dl.acm.org/doi/fullHtml/10.1145/3571884.3597130
        
         | mritchie712 wrote:
         | I made something called `ultraplan`. It's is a CLI tool that
         | records multi-modal context (audio transcription via local
         | Whisper, screenshots, clipboard content, etc.) into a timeline
         | that AI agents like Claude Code can consume.
         | 
         | I have a claude skill `/record` that runs the CLI which starts
         | a new recording. I debug, research, etc., then say "finito" (or
         | choose your own stopword). It outputs a markdown file with your
         | transcribed speech interleaved with screenshots and text that
         | you copied. You can say other keywords like "marco" and it will
         | take a screenshot hands-free.
         | 
         | When the session ends, claude reads the timeline (e.g. looks at
         | screenshots) and gets to work.
         | 
         | I can clean it up and push to github if anyone would get use
         | out of it.
        
           | wanderingmind wrote:
           | Sounds interesting I would love to use it if you get a chance
           | to push to github
        
             | mritchie712 wrote:
             | https://github.com/definite-app/ultraplan
        
           | heliostatic wrote:
           | Definitely interested in that!
        
             | mritchie712 wrote:
             | Added link above!
        
           | mritchie712 wrote:
           | https://github.com/definite-app/ultraplan
        
       | bn-usd-mistake wrote:
       | Does anyone have a similar mobile application that works locally
       | and is not too expensive? Mostly looking to transcribe voice
       | messages sent over Signal which does not offer this OOTB
        
         | bogtap82 wrote:
         | There is one single app I've been able to find that offers
         | Parakeet-v3 for free locally and it's called Spokenly. They
         | have paid cloud models available as well, but the local
         | Parakeet-v3 implementation is totally free and is the best STT
         | has to offer these days regardless. Super fast and accurate. I
         | consider single-user STT basically a solved problem at this
         | point.
        
           | kuatroka wrote:
           | Spokenly is great too, but Handy's minimalistic and focused
           | UI won me over.
        
           | dumbmrblah wrote:
           | Spokenly is my go-to app on iOS for transcription as well.
        
         | 4mitkumar wrote:
         | I have been using this one from Futo for quite some time and
         | love it: https://keyboard.futo.org/
         | 
         | They also have a voice input only version if you still would
         | like to keep your typing keyboard: https://voiceinput.futo.org/
        
       | miniwark wrote:
       | Did this thing (or open-whispr) work well with other languages
       | than english ?
        
         | dawkins wrote:
         | In Spanish works very well
        
         | wi5eif6E wrote:
         | German also works great.
        
       | kuatroka wrote:
       | Love it. I had been searching for STT app for weeks. Every single
       | app was either paid as a one off or had a monthly subscription.
       | It felt a bit ridiculous having to pay when it's all powered by
       | such small models on the back end. So I decided to build my own.
       | But then I found "Handy" and it's been a really amazing partner
       | for me. Super fast, super simple, doesn't get in my way and it's
       | constantly updated. I just love it. Thanks a lot for making it!
       | Thanks a lot
       | 
       | P.S. The post processing that you are talking about, wouldn't it
       | be awesome.
        
       | skor wrote:
       | This is so handy, thank you very much. Good work!!
        
       | aucisson_masque wrote:
       | It's incredibly fast on my MacBook m1 air and more accurate that
       | the native speech to text.
       | 
       | The ui is well thought out, just the right amount of setting for
       | my usage.
       | 
       | Incredible !
       | 
       | Btw, do you know what << discharging the model >> does ? It's set
       | to never by default, tried to check if it has an impact on ram or
       | cpu but it doesn't seem to do anything.
        
         | mixtureoftakes wrote:
         | the model is permanently loaded into ram for access speed.
         | discharging it would unload it from ram and lead to longer
         | start times
        
           | sipjca wrote:
           | It does unload it, and actually might be a good default for
           | most people as the model loading does happen in the
           | background as soon as you hit the key
        
       | wi5eif6E wrote:
       | This looks and works great! A settings option to keep no
       | recording history at all would be terrific.
        
       | qprofyeh wrote:
       | As a Mac user, am I missing something? macOS has Dictation built-
       | in, when you short press F5 it should start transcribing your
       | spoken words into text in real time. It even does non-English
       | languages.
        
         | luigi23 wrote:
         | it's trash if:
         | 
         | - you're not a native speaker or have accent
         | 
         | - using airpods mic
         | 
         | - surroundings is noisy
         | 
         | - use novel words like 'claude code'
         | 
         | - mumble a bit
        
         | d4rkp4ttern wrote:
         | Besides being trash as others said, there's a trade off with
         | real time transcription word by word - there's no opportunity
         | for an AI to holistically correct/clean up the transcription
        
           | SkyPuncher wrote:
           | But, OSX does come back and fix things.
        
             | d4rkp4ttern wrote:
             | You mean, after displaying each word as it is spoken, then
             | OSX goes back and fixes what's been displayed? I think I've
             | seen it fix one or two recent words, but I guess you're
             | saying it could fix the entire sentence as well. I didn't
             | know that
        
       | laylower wrote:
       | Is it deployed locally or does it send data to your servers?
        
         | sipjca wrote:
         | It's all local
        
           | mixtureoftakes wrote:
           | Which model would be the best to use for mandarin? Are there
           | any models on par with Parakeet that are just as fast but
           | also understand Chinese?
        
             | mixtureoftakes wrote:
             | also is there a way to make parakeet type more naturally?
             | less capitallization, less punctuation? can this be a
             | setting?
             | 
             | this can already be done via local llm processing the text
             | but surely there is an easier way to do this, right
        
       | walthamstow wrote:
       | Nice. I spent most of Christmas vibe coding with Google
       | Antigravity with one hand while holding a sleeping baby in the
       | other. MacOS built in dictation is OK, but struggles with
       | technical language.
        
       | d4rkp4ttern wrote:
       | I've tried several, including this one, and I've settled on
       | VoiceInk (local, one-time payment), and with Parakeet V3 it's
       | stunningly fast (near-instant) and accurate enough to talk to
       | LLMs/code-agents, in the sense that the slight drop in accuracy
       | relative to Whisper Turbo3 is immaterial since they can "read
       | between the lines" anyway.
       | 
       | My regular cycle is to talk informally to the CLI agent and ask
       | it to "say back to me what you understood", and it almost always
       | produces a nice clean and clear version. This simultaneously
       | works as confirmation of its understanding and also as a sort of
       | spec which likely helps keep the agent on track.
       | 
       | UPDATE - just tried handy with Parakeet v3, and it works really
       | well too, so I'll use this instead of VoiceInk for a few days. I
       | just also discovered that turning on the "debug" UI with Cmd-
       | shift-D shows additional options like post processing and
       | appending trailing space.
        
         | thethimble wrote:
         | I wish one of these models was fine tuned for programming.
         | 
         | I want to be able to say things like "cd ~/projects" or "git
         | push --force".
        
           | netghost wrote:
           | I'll bet you could take a relatively tiny model and get it to
           | translate the transcribed "git force push" or "git push dash
           | dash force" into "git push --force".
           | 
           | Likewise "cd home slash projects" into "cd ~/projects".
           | 
           | Maybe with some fine tuning, maybe without.
        
       | ekjhgkejhgk wrote:
       | Explain to me why a speech-to-text app has 50% of its code in
       | typescript...?
        
         | beklein wrote:
         | Not the author/contributor, but the app is built using Tauri
         | for easy multi-platform support, so the backend logic is
         | implemented in Rust and the frontend UI is implemented in
         | TypeScript. I think it's a valid choice. GitHub does not
         | include any model _code_ in the stats; the models will be
         | downloaded separately the first time you use them. Hope this
         | helps.
         | 
         | I know many people hate sites like this, but I actually like
         | them for these use cases. You can get a quick, LLM-generated
         | overview of the architecture, e.g. here:
         | https://codewiki.google/github.com/cjpais/handy
        
       | holtwick wrote:
       | FluidVoice for macOS is pretty handy as well. Open source under
       | Apache License. https://altic.dev/fluid https://github.com/altic-
       | dev/FluidVoice
        
         | jimmydoe wrote:
         | Its vibe coded UI feels too complicated.
        
       | Jayakumark wrote:
       | Its great, i have been using it . Two requests though 1. iOS app
       | 2. API option to use against meeting transcription or route audio
       | from Mic .
        
         | blensor wrote:
         | +1 on the meeting tranecription
        
       | unutranyholas wrote:
       | https://hex.kitlangton.com/ is good
        
       | sirjaz wrote:
       | This is great, and I love that this is not another webapp
        
       | oybng wrote:
       | On Windows this depends on webview2, which the installer attempts
       | to download. No mention of this requirement in the readme. It's a
       | shame this software isn't portable
        
       | erelong wrote:
       | WhisperTux on linux worked ok, curious how Handy compares:
       | https://github.com/cjams/whispertux
        
       | mnmalst wrote:
       | This is really cool. Works out of the box and I'm typing this
       | using handy.
       | 
       | Is there any way to execute commands directly on Linux?
       | 
       | Also a feature to edit or correct already typed text would be
       | really great.
        
       | mncharity wrote:
       | A cautionary user experience report. The default hotkey upon
       | download is ctrl+space. Press to begin recording, release to
       | transcribe and insert. Key-up on the space key constitutes hotkey
       | release. If the ctrl key is still down when the insertion lands,
       | the transcribed text is treated as ctrl characters. The test app
       | was emacs. (x64 linux x11, with and without xdotool)
        
       | peterldowns wrote:
       | Huge fan! Parakeet v3 works great with it. I have used Monologue,
       | Superwhisper, and Aqua, at various times in the past. But Handy
       | is at least as good, and it's not an expensive subscription. I
       | love that it runs locally, too. Strongly recommend!
        
       | Barbing wrote:
       | _Quick thoughts re: mentioned transcribers_
       | 
       |  _Superwhisper_ -- Been using it a long time. It 's paid with a
       | lifetime subscription available. Tons of features. Language
       | models are built right in without additional charge. Solo dev is
       | epic; may defer upgrades to avoid occasional bugs/regressions
       | (hey, it's complex software).
       | 
       | Trying each for a few minutes:
       | 
       |  _Hex_ -- Feels the leanest ( & cleanest) free options mentioned
       | for Mac in this thread.
       | 
       |  _Fluid Voice_ -- Offers a unique feature, a real-time view of
       | your speech as you talk! Superwhisper has this, but only with an
       | online model. (You can 't see your entire transcript in Fluid,
       | though. The recording window view is limited to about one
       | sentence at a time--of course you do see everything when you
       | complete your dictation.)
       | 
       |  _Handy_ -- Pink and cute. I like the history window. As far as
       | clipboard handling goes, I might note that the  "don't modify
       | clipboard" setting is more of a "restore clipboard" setting.
       | Though it doesn't need as many permissions as Hex because it's
       | willing to move clipboard items around a bit, if I'm not
       | mistaken.
       | 
       | Note Hex seems to be upset about me installing all the others...
       | lots of restarting in between installs all around. Each has
       | something to offer.
       | 
       | ---
       | 
       | Big shout out to Nvidia open-sourcing Parakeet--all of these apps
       | are lightning fast.
       | 
       | Also I'm partial to being able to stream transcriptions to the
       | cursor into any field, or at least view live like Fluid (or
       | superwhisper online). I know it's complex b/c models transcribe
       | the whole file for accuracy. (I'm OK with seeing a lower quality
       | transcript realtime and waiting a second for the higher-quality
       | version to paste at the end.)
        
       | fittingopposite wrote:
       | Is there any good android app featuring parakeet v3?
        
       ___________________________________________________________________
       (page generated 2026-01-15 23:01 UTC)