Vito vs Aqua Voice
Aqua Voice is one of the newer, well-funded AI dictation apps: fast, polished, and genuinely good at technical and coding vocabulary. Vito does the same core job — speak, get clean text anywhere — but takes the opposite side on almost every choice: free and open instead of a subscription, on Linux, and paid by the hour rather than by the month. Here is an honest account of where each one wins, written by the people who make Vito and checked against Aqua's own pages.
At a glance
| Vito | Aqua Voice | |
|---|---|---|
| Cost | Free app, ~€0.15 per hour of speech to your own provider | $8/month billed annually (Pro); Team $12/user |
| Free option | Free path: AssemblyAI credit + Groq's free tier, no card | 1,000 words, one time |
| Choose the cleanup AI | Yes — any OpenAI-compatible model, local included | No |
| Windows | Yes | Yes |
| macOS | Planned | Yes |
| Linux | Yes | No |
| iPhone | No | Yes |
| On-screen context for code | No | Yes |
| Dictation languages | 60 | 49 |
| Account | None | Required |
| Source code | Open | Closed |
Checked against aquavoice.com in July 2026.
Where Aqua Voice is the better choice
You are on a Mac or an iPhone
Aqua runs on macOS and has an iPhone app, with one account across your devices. Vito runs on neither yet — macOS is planned, there is no mobile version. If your machine is a Mac, this is close to the end of the discussion.
You want it working in the next two minutes
Download, sign in, dictate. No API keys, no providers to choose, no balance to top up. Vito's bring-your-own-key model is cheaper to run but it does ask you to set up an account or two first. If you would rather not, Aqua removes that step entirely.
You dictate code and technical prose
This is Aqua's real strength and worth naming plainly. It reads on-screen context to get syntax, symbols and technical terms right, which is exactly where general dictation tends to fall apart. If a lot of what you dictate is code or jargon, that is a genuine advantage Vito does not match.
You would rather one predictable bill
A subscription is a fixed, known number every month. Vito's by-the-hour cost is usually lower but it is a variable you have to be comfortable with. Some people simply prefer the flat fee, and that is a fair preference.
Where Vito is the better choice
You are on Linux
Aqua does not run on Linux. Vito does, and goes further than most: it detects missing system utilities and explains hotkey setup per desktop environment. For a Linux user this is the clearest difference between the two.
The cost, if you dictate a normal amount
Vito costs about €0.15 per hour of speech. Aqua Pro is $8 a month billed annually — roughly $96 a year, whether you dictate or not. You would have to speak for something like fifty hours in a month before Vito's usage cost caught up with that, and if you use it less, the gap only widens. And you can start for nothing: pair AssemblyAI's free starting credit with Groq's free tier and Vito runs at no cost, no card required.
You want a say in which AI cleans your text
Aqua's refinement is Aqua's, take it or leave it. Vito's cleanup step talks to any OpenAI-compatible endpoint, so you choose the model that rewrites what you said — a frontier model when you want the best result, or a local LLM on your own machine when you would rather that step never leave it. (The speech-to-text still goes to your chosen provider, so this is about the cleanup, not full offline dictation.)
You want to read the code, and own your keys
Vito is open source, so its privacy claims are checkable rather than promised. It has no account, your keys stay on your machine and are yours to use elsewhere, and there is nothing to cancel. Aqua is closed source and account- based; to their credit they say transcripts are not stored on their servers, but with Vito you can read exactly what happens instead of taking anyone's word.
It is quite good fun
A small thing, and we are not going to pretend it decides anything. Vito keeps count: words dictated, sentences cleaned up, hours of typing you did not have to do, a chart of your week. There are 40+ achievements to unlock along the way, some of them silly, several of them hidden.
It turns out to matter more than it sounds like it should. Dictating instead of typing is a habit you have to build, and the first week is the awkward part — seeing "1 h 38 m of typing saved" is a nudge to keep going that a blank window does not give you. If that sounds like a gimmick to you, ignore it entirely; nothing depends on it.
About that free tier
Aqua's free plan is 1,000 words, one time — a taste, not a tier. It is enough to see whether you like it, which is a fair way to try something, but it runs out fast and the only step up from there is the subscription.
Vito's free path is a running one, not a sample
Because Vito brings your own keys, its "free" comes from the providers: AssemblyAI gives new accounts starting credit and Groq's cleanup has a free tier, and neither needs a card. Pair them and you are doing real dictation for nothing — and when you outgrow the free allowances it is pennies an hour, not a jump to a monthly plan.
What they both do
Both put finished text — not a raw transcript — wherever your cursor is, in any application, from a single hotkey, cleaning up the hesitations and the false starts as they go. If that is all you need and you are on a Mac, Aqua is an excellent version of it. The differences above are about everything around that core.
So which one
- On a Mac or iPhone? Aqua. Vito isn't there yet.
- On Linux? Vito, by default.
- Dictating a lot of code? Aqua's context awareness is a real edge.
- Want the lowest cost, or free? Vito.
- Want open source and no account? Vito.
- Prefer one flat monthly bill and zero setup? Aqua.