Independent outdoor mobility using a chin-controlled power wheelchair.
My name is Andrei Cebotar. I’m 37, I live in Moldova, and I have Spinal Muscular Atrophy.
My hands get tired fast — by the end of the day I often can’t feel them at all. I can press one mouse button. That’s mostly what I have to work with. And yet I play games, I write, I have conversations online. This is how.
This isn’t a neutral roundup. These are the tools I use to access my computer and play games. Some of them are part of my daily routine, others I tried and eventually stopped using. What works for me may not work for everyone, but this is the setup I’ve built around my own needs.
PlayAbility — my face is my controller
PlayAbility is a free Windows app that maps facial expressions and head movements to any game input. You set it up through a webcam — no extra hardware. And it works with any PC game that accepts a standard controller or keyboard.
Here’s what my setup actually looks like in practice: I raise both eyebrows — my character jumps. I raise my left cheek — I drink a potion. I raise my right cheek — I activate a specific skill. These are real mappings I use in real games, right now.
What makes this work is that the gestures feel natural after a while. You stop thinking “raise left cheek” and just do it. The response is fast enough that it doesn’t break the flow of gameplay. And because it creates a virtual Xbox controller in the background, the game has no idea you’re not using a standard input — no mods, no special settings needed.
It also works outside of games. You can map expressions to mouse clicks, scrolling, keyboard shortcuts. For someone with one working mouse button, that’s not a small thing.
PlayAbility is free. There’s a paid Pro version if you want unlimited profiles, but everything works without paying.
Handy — I speak, it types
Handy is a free, open-source speech-to-text app. You press a shortcut, speak, release — and your words appear in whatever text field your cursor is in. Any app, any website, anywhere on your computer.
I use it every single day. It has genuinely changed how I communicate. Typing is physically expensive for me — Handy removes that cost almost entirely for text. Messages, emails, search boxes — I speak instead of type.
What sets it apart from Windows Voice Access or cloud dictation tools is that it processes audio locally. Your voice never leaves your computer. It’s also simpler — one job, done well. Press, speak, done.
I used Windows Voice Access before Handy. It helped, but the accuracy wasn’t great. Handy is noticeably more reliable, and the local processing means it works without an internet connection.
Xbox Adaptive Controller — the foundation I build on
For a long time I didn’t use a standard keyboard at all. Instead I used the Razer Tartarus — a one-handed keypad with a stick and programmable buttons. It let me build exactly the macros I needed without reaching across a full keyboard. For someone with limited hand mobility, the compact layout and low-force buttons make a real difference.
More recently I moved to the Xbox Adaptive Controller, and it’s more flexible. It’s not a controller by itself — this is important to understand before you buy it. It’s a hub: a large flat surface with two big buttons and a row of 3.5mm ports on the back, each of which accepts an external switch, joystick, or pedal. You build the layout around your body, not the other way around.
I use it with a joystick and switch buttons. The physical switches require very little force — that matters when your hands tire quickly.
It works on PC and Xbox. If you’re on PlayStation, Sony has their own equivalent — the PlayStation Access Controller, which works on the same principle.
The Logitech Adaptive Gaming Kit is worth knowing about too — it’s a set of buttons, triggers, and switches designed to plug into the Xbox Adaptive Controller. It gives you more options without spending a lot.
Tobii Eye Tracker — useful, but I stopped using it
The Tobii Eye Tracker 5 sits below your monitor and tracks where you’re looking. In games, it moves the camera in the direction of your gaze. I used it to play Kingdom Come: Deliverance — wherever I looked, the camera followed. For an open-world RPG, that’s genuinely immersive and reduces the need to constantly move a stick just to look around.
The problem for me was physical. After extended sessions, my eyes hurt — the infrared tracking seemed to cause strain over time. I eventually stopped using it for that reason.
One thing worth knowing: Tobii’s native game integration moves the camera, but it doesn’t control your mouse cursor by default. For that you need a separate app called Project IRIS. It lets you control the mouse pointer with your gaze and set up interaction zones on your desktop — areas you look at to trigger actions like clicks or keypresses. It costs €39 and works with Tobii EyeX, 4C, and Eye Tracker 5. If you want to use eye tracking beyond games — for navigating Windows, browsing, anything — IRIS is what makes that possible.
If eye strain isn’t an issue for you, it’s worth trying. Eyeware Beam is a software alternative that uses a regular webcam or iPhone instead of dedicated hardware — cheaper, slightly less precise, but no infrared involved.
Talon Voice — powerful, but not for me
I also tried Talon Voice. It’s a free, highly capable hands-free input system — voice control, noise recognition, eye tracking, all combined. You can theoretically control your entire computer without touching anything: move the mouse, click, type, run scripts, even code.
The problem for me was false positives. Too many unintended triggers — the system would pick up ambient sounds or normal speech and fire commands I didn’t mean to send. Managing that became more work than the tool was saving me. I moved on.
That said, Talon has a large and active community, and people who invest time in configuring it properly seem to get a lot out of it. It’s also worth noting that it has a significant learning curve — the setup is technical, and it’s not a plug-and-play experience. If you’re comfortable tinkering, it might be worth exploring. If you want something that works quickly without deep configuration, Handy is a much simpler starting point for dictation.
The combination is the point
None of these tools solves everything on its own. What actually works is layering them. Right now, on a typical day, I’m using PlayAbility for in-game actions, Handy for any text I need to write, and the Xbox Adaptive Controller for movement. Each covers what the others can’t.
If you have SMA, cerebral palsy, muscular dystrophy, or any condition that limits fine motor control — the starting point I’d suggest is PlayAbility and Handy. Both are free, both require nothing beyond a webcam and microphone, and both can meaningfully change what’s possible at a computer, not just in games.
The hardware — adaptive controllers, eye trackers — comes later, once you know what gaps remain.
In a follow-up piece, I write about where I think this is all heading — specifically, EMG wristbands and what they could mean for people like me. But that’s the future. This is what works right now.
The Handy logo. Handy is a speech-to-text and augmentative and alternative communication (AAC) application.
Free. Open-source. Offline. And no, there’s no catch.
Imagine an app that does exactly what you ask, nothing more, nothing less — no subscription pop-ups, no word limits, no account to create, no server quietly sipping your voice data in the background. That’s Handy in a nutshell. And in a world where every other dictation tool seems to be one pricing tier away from truly working, that alone feels almost radical.
Handy was born out of necessity. Developer CJ Pais built it after a finger injury made typing genuinely painful. He needed a simple, reliable way to speak text into any app on his computer, and when nothing out there satisfied him, he made it himself. The result is a lean, no-nonsense speech-to-text tool that now sits at over 23,000 GitHub stars and keeps shipping new versions at a pace that would embarrass many commercial products.
But for some people, Handy isn’t just a convenience tool. It’s something more fundamental than that.
A Personal Story: When Typing Stops Being an Option
I have a progressive illness. For a long time, I typed with one finger — slowly, carefully, one hand doing the work of two. Fifteen minutes was about my limit before my hand started protesting. Then even that became too much, and I found myself reduced to short phrases, a couple of words at a time. Conversations became exhausting. Writing an email could take days.
For a while, I switched to an on-screen keyboard and a mouse. The built-in autocomplete made it manageable — surprisingly usable, actually — but overworking that one remaining finger eventually caused inflammation, and the cycle repeated. Back to short phrases. Back to silence.
Then Microsoft released their Voice to Speech feature in a Windows update, and for a while it felt like a lifeline. I could speak again. I could write again. Real messages, real length, real conversations — not just a word or two squeezed out between rests. But the tool was unreliable. It made a lot of errors, froze regularly, and the recognition quality just wasn’t there for serious use.
The breakthrough came through a friend. We were both dealing with similar situations — he has SMA too — and when I showed him the Microsoft tool, it turned out his older Windows version didn’t support it at all. So we went looking for something else. And we found Handy.
It’s not an exaggeration to say it changed things. Fast, accurate, works in whatever app is active, supports multiple languages including English, Romanian and Russian, completely free. For two people who had spent years adapting to shrinking communication windows, getting that back was quietly significant.
I mention this not to make the review sentimental, but because it’s context that matters. Handy gets reviewed mostly by developers and tech enthusiasts who treat it as a workflow optimisation. That’s a legitimate perspective. But the app also quietly serves people for whom it’s less about convenience and more about participation — in conversations, in correspondence, in ordinary online life. The fact that it’s free, open-source, and doesn’t require an account or a subscription isn’t just a nice detail. For some users, it’s what makes it accessible at all.
CJ Pais built Handy after a hand injury. Some of his users are still dealing with theirs.
What Handy Actually Does
The pitch is beautifully simple: hold a hotkey, speak, let go — and your words appear in whatever text field currently has focus. Browser, code editor, notes app, messenger, email client — Handy doesn’t know or care what’s open. It just pastes the transcription and gets out of your way.
Everything happens locally. When you speak, no audio is sent to any server. The model runs right on your machine, processes what you said after you stop speaking, and delivers the result in roughly 2 to 5 seconds. It’s not instant — that’s one of Handy’s honest trade-offs — but your voice stays yours.
Key Features, Honestly Described
General settings — hotkey configuration, push-to-talk mode, microphone and audio options.
Push-to-talk by default — hold the hotkey while you speak, release when you’re done. There’s also a toggle mode if you’d rather not hold anything. The shortcut is fully configurable from the General tab.
Auto-paste — the transcribed text lands directly in whatever app you’re using, no copy-paste step needed. One caveat: if you switch windows during the 2–5 second processing window, it can paste in the wrong place. Stay focused and it works beautifully.
Language and translation — language can be set to Auto Detect or locked to a specific one. Some models also support optional translation to English, toggled right from the General settings.
Voice Activity Detection (Silero VAD) — Handy trims silence from your recordings before processing. You don’t have to be precise about when you stop speaking; it handles the cleanup.
Advanced settings — paste method, clipboard behaviour, custom word list, and experimental features.
Custom word lists — you can train Handy to recognise names, jargon, technical terms, and anything else the base models tend to mangle. Words are added one by one from the Advanced tab.
Paste Method — by default Handy uses Clipboard (Ctrl+V), but this can be changed in Advanced settings depending on your system and workflow.
Start Hidden / Launch on Startup / Tray Icon — Handy is designed to live quietly in the background. Toggle these from Advanced to make it fully invisible until you need it.
Overlay Position — a small recording indicator appears on screen while you speak; you can pin it to the bottom, top, or corners.
Command-line interface — a full CLI for scripting, automation, and integration into development workflows.
Raycast extension on macOS — for Mac users who live inside Raycast, Handy plugs in natively.
Recording history — your recent transcriptions are stored locally in the History tab so you can revisit them at any time.
Post Process tab — connect any OpenAI-compatible LLM to clean up, reformat, or transform your transcription.
LLM post-processing — the Post Process tab lets you connect any OpenAI-compatible API (OpenAI, local models via Ollama, or others) to run a custom prompt over your transcription after it’s done. Clean up filler words, reformat into bullet points, summarise — whatever prompt you write. You can create and save multiple named prompts and trigger them with a dedicated hotkey (Ctrl+Shift+Space by default).
Platform Support: The Linux Story
Here’s where Handy separates itself from almost everything else in the dictation space: it runs on Linux.
macOS has no shortage of polished dictation apps. Windows is covered. Linux users have historically been stuck with whatever their distro’s built-in accessibility tools could manage. Handy supports Ubuntu 22.04 and 24.04 out of the box, with Wayland and X11 both handled.
This alone has made Handy something of a cult favourite in the Linux and open-source communities.
Privacy: The Simplest Story Possible
There is no cloud transcription mode. There is no telemetry pipeline. There is no account, no profile, no usage data being collected. The only network activity Handy performs is downloading models when you first set it up, and optionally checking for updates.
Since the code is MIT-licensed and publicly available on GitHub, anyone who wants to verify these claims can read every line of it.
Under the Hood: Every Model, Explained
Handy isn’t locked to a single AI engine — it lets you choose from a broad lineup of local speech models. The right choice depends on your language, hardware, and how much you care about accuracy vs. speed. All models run entirely on your machine; none send audio to the cloud.
The Models screen — downloaded models at the top, available for download below. Whisper Large is currently active.
At a Glance
Model
Size
Languages
Speed
Best For
Whisper Large ★
~1.1 GB
99+
Slower
Maximum accuracy, multilingual
Whisper Turbo
~1.5 GB
99+
Moderate
Speed + quality balance
Whisper Medium
~469 MB
99+
Moderate
Good all-rounder
Whisper Small
~465 MB
99+
Fast
Low-resource multilingual
Parakeet V3 ★
~478 MB
25 European
Fast
Best default, CPU-only
Parakeet V2
~451 MB
English only
Fast
English speed
GigaAM v3
~225 MB
Russian only
Fast
Best Russian model
Canary 1B v2
~692 MB
25 European
Moderate
European + translation
Canary 180M Flash
~146 MB
4 languages
Fast
Lightweight translation
Breeze ASR
~1.0 GB
Multilingual
Moderate
Taiwanese Mandarin
SenseVoice
~152 MB
5 East Asian
Fastest
Chinese/Japanese/Korean
Moonshine Base
~55 MB
English only
Very fast
Ultra-light English
Moonshine V2 Tiny
~31 MB
English only
Fastest
Minimum footprint
Moonshine V2 Small
~99 MB
English only
Very fast
Speed + accuracy balance
Moonshine V2 Medium
~192 MB
English only
Fast
Better English quality
Custom GGML
any
depends
depends
Power users
★ My personal daily drivers — for different reasons, as explained below.
The model family that started the local speech-to-text revolution. Supports 99+ languages and optional translation to English. One important caveat across all Whisper variants: they can hallucinate — inventing words during silences. It doesn’t show up in benchmarks, but it shows up in real use.
Whisper Large (~1.1 GB) — My primary model.
The flagship. Highest accuracy across all 99+ languages, best on accents, technical vocabulary, and complex sentence structure. Slow — expect 3–5 second delays — and needs a capable GPU on Windows/Linux. But when accuracy matters most, nothing in the Whisper family beats it.
Whisper Turbo (~1.5 GB)
Optimised for speed without sacrificing much quality. A strong choice for Apple Silicon users. Doesn’t support translation. Can be unstable on some Windows/Linux GPU setups.
Whisper Medium (~469 MB)
The sensible middle ground. Good accuracy, reasonable speed, supports translation. A solid all-rounder.
Whisper Small (~465 MB)
The lightest Whisper. Fast and low on resources. Accuracy is the weakest in the family — struggles more with accents and background noise.
NVIDIA’s open answer to Whisper — Apache 2.0 licensed, lower hallucination rate, runs CPU-only. Numbers come out as words rather than digits. Auto-detects language.
Parakeet V3 (~478 MB) — My second daily driver, and the one I’d recommend to most people first.
Fast, accurate, CPU-only, automatic language detection across 25 European languages including Romanian and Russian. On Apple Silicon it approaches near-real-time.
Parakeet V2 (~451 MB)
English only. Largely superseded by V3.
The best Russian speech recognition model in Handy. Trained on 700,000 hours of Russian speech data. Outperforms Whisper Large on Russian benchmarks by a significant margin. Small footprint (~225 MB), fast, CPU-only. If you dictate in Russian, this is the model to use.
Transcription and translation across European languages. Important: Canary does not auto-detect language — always set it manually, otherwise it translates instead of transcribing.
Canary 1B v2 (~692 MB) — 25 European languages, full translation, high accuracy. Canary 180M Flash (~146 MB) — English, German, Spanish, French only. Fast and light.
Breeze ASR
Optimised for Taiwanese Mandarin with code-switching support — handles sentences that mix Mandarin and other languages mid-phrase. Around 1.0 GB. The best Handy option for Taiwanese Mandarin.
The fastest model in the lineup. Covers Chinese (Mandarin and Cantonese), English, Japanese, and Korean. At ~152 MB it’s compact and transcribes extremely quickly. Ideal for East Asian language users who want the fastest possible response time.
English-only models built for efficiency. Despite their tiny size, they match or beat Whisper Large on English benchmarks. Low hallucination rate, CPU-only.
Moonshine V2 Tiny (~31 MB) — the smallest model in all of Handy. Nothing lighter exists. Moonshine V2 Small (~99 MB) — good balance of speed and quality. Moonshine V2 Medium (~192 MB) — better accuracy, still fast. Recommended Moonshine pick. Moonshine Base (~55 MB) — original model. Very fast, good on accents.
Custom GGML Models
Any Whisper-compatible .bin model file dropped into Handy’s models/ folder will appear in the picker on next launch. No official support — quality depends entirely on the model you bring.
How to Choose
Starting fresh? → Parakeet V3. Fast, smart, works on CPU, handles English, Romanian and Russian.
Need maximum accuracy? → Whisper Large.
Dictating in Russian? → GigaAM v3. It’s not even close.
Need translation too? → Canary 1B v2.
Old or low-powered hardware? → Moonshine V2 Medium or Moonshine Base.
East Asian languages? → SenseVoice.
Taiwanese Mandarin? → Breeze ASR.
Absolute minimum footprint? → Moonshine V2 Tiny at 31 MB.
The Trade-Offs (Because Nothing is Perfect)
Handy doesn’t clean up your words — you get verbatim output, exactly what the model heard. There’s no AI rewriting, no filler-word removal, no tone adjustment. If you want polished text, you’ll do that editing yourself.
There’s no mobile app. Handy is desktop-only.
The transcription delay — that 2 to 5 second window after you stop speaking — is a real workflow adjustment. Occasionally the first word or two of a transcription gets clipped. Bluetooth microphones add another second or two of latency, though the “Always-On Microphone” setting largely solves that.
None of this is dealbreaking for what Handy is. It’s a young open-source project, version 0.8.3 as of mid-2026, and the version numbering is the developer’s candid way of saying: we’re still building this, but what’s here works.
The Bottom Line
Handy is the rare piece of software that does exactly what it says, costs nothing, respects your data completely, and actually ships updates. The project has real momentum, a growing community, and a developer who built it to scratch his own itch — which is historically how the best tools get made.
For developers and power users, it’s a flexible, hackable, privacy-respecting dictation layer that fits into any workflow. For people who type with one finger, or can’t type at all — it’s something quieter and more important than that. It’s a way back into the conversation.
It’s not trying to be everything. It’s trying to be one thing, done well. And for a lot of people, that’s more than enough.
Immersing into the game: AI facial tracking bridges the gap between the player and the fantasy world.
For a long time, adaptive gaming relied almost entirely on hardware solutions: hubs with dozens of ports, custom switches, and specialized joysticks. Today, Artificial Intelligence is providing new options, turning a standard webcam and microphone into highly capable supplementary tools. Instead of the user constantly adapting to the interface, software is helping the interface adapt to the user’s needs.
The software interface in action: mapping head movements and facial expressions directly to mouse controls.
Optical Tracking: Pixels Instead of Plastic At the core of these technologies are computer vision algorithms that track facial landmarks in real time. For example, Google’s experimental Project Gamefacereads facial expressions and head movements, translating them into basic in-game actions.
A practical, available example of this is the PlayAbility software. It acts as a system-level translator for Windows, allowing games to recognize facial inputs as standard gamepad presses:
Tracking Expressions: The software monitors changes in your facial features. You can map actions to specific movements, such as furrowing your brows to aim or using a slight smirk to activate a trigger.
Alternative Camera Control: Smooth head tilts and turns can be converted into mouse cursor movements or the right analog stick, providing another way to control the camera.
Hybrid Ecosystems: The program allows you to combine a webcam, microphone, keyboard, and physical adaptive controllers into a single profile. Notably, the base version of PlayAbility is currently free.
Hands-On Experience: Testing PlayAbility in Diablo 4 To see how well this works in practice, I recently tested PlayAbility during a two-hour session in Diablo 4. My goal was to offload some of the fast-paced inputs from my physical setup.
I configured the software to handle three specific actions: using a health potion, jumping/evading, and casting one of my skills. I mapped these actions to three distinct facial triggers:
Raising my eyebrows
Lifting my left cheek
Lifting my right cheek
The key actuation was highly precise. I was impressed by how accurately and reliably the program responded to my specific triggers. It successfully handled the inputs without frustrating misfires, proving to be a viable addition to an action-heavy game.
Classic Voice Control For those who prefer not to use facial tracking or just want to offload specific inputs, there are programs dedicated exclusively to voice control, such as VoiceBot and VoiceAttack.
These are practical solutions for triggering macros. VoiceBot, for instance, allows users to write advanced scripts (including in C#) and tie chains of commands to a single word. Such programs work well in tandem with tools like AutoHotkey, shifting routine or complex tasks to quick voice commands.
Building Custom Interfaces The main advantage of these systems lies in their software-driven flexibility. Users can build a unified setup where physical adaptive switches work alongside facial expressions and tuned voice scripts. While it’s not a magic bullet that removes all barriers, it significantly reduces physical fatigue and helps create a much more comfortable, personalized gaming experience.
