Shuovo

“Shuo” is 说 (shuō, to speak); “vo” is 我 (wǒ, me) — 说我, “speak my mind.”

Ordinary dictation cuts you off when you pause.
Shuovo knows that’s when the thinking starts.

A voice keyboard for thinking out loud. Pause for twenty seconds to check something, switch to another app, mix Chinese and English in one sentence. When you stop, one clean draft lands where your cursor was — an AI chat, a message, a doc — on Android and in Chrome.

Free to install. Voice has a 14-day free trial.

Five weeks of the founder’s own use: 509 sessions, 17 a day. One in three ran past a minute; the longest ran 19. Four in ten seconds were silence. One in three was in Chinese, or both languages at once.

One pause. Two outcomes.

What you said

“So the target has to be single digits. Maybe one error in a thousand. Right now it’s about…”

14 seconds of silence — remembering a number

“…three to five percent, if I remember correctly. Slightly higher for the other one. But my main point is each provider has its own data.”

Ordinary dictation

Stops at the pause.

“So the target has to be single digits. Maybe one error in a thousand. Right now it’s about”

Sent as it stands. The rest is a second recording — if you notice in time.

Shuovo

Waits while you think.

The target has to be single digits — maybe one error in a thousand. Right now it’s three to five percent, slightly higher for the other provider, and each provider has its own data.

One draft, in the chat that was already open.

From a real 8.7-minute session, lightly edited — one of 509 in five weeks. Four in ten seconds of them were silence. That is where the thinking happened, and where ordinary dictation hangs up.

Start with 20 seconds

Losing a sentence is annoying. Losing eight minutes of thinking isn’t. Try Shuovo here for twenty seconds, see what comes back, and decide whether it earns a longer session.

Ready when you are.

0:00

Text to edit

In the app you’d select text and speak. Here, your spoken instruction is applied to this sample — feel free to change it.

Try saying

Okay, so the part I’m not happy with is the accuracy. One idea — and it might not be the best one — is to run the audio through several models and compare. Actually, let me think about what that costs first…

Result

Show raw transcription

This demo runs on separate, smaller infrastructure than the app, and takes short clips only.

The Android app and Chrome extension are free to install. Voice is a subscription — 14 days free, then $15/month — with no session cap.

What Shuovo is built for

Silence is not a hang-up
Dictation is built for a text message. Shuovo is built for debugging a laptop that won’t boot, weighing an architecture trade-off, arguing strategy with an AI. Pause to find a file. Open another app and read the error. The session is still running when you come back — thirty seconds in or nineteen minutes in.

No session cap; the founder’s longest ran 19 minutes. Your audio is saved as you speak, so a dropped connection or a crash doesn’t take it with it, and a recording that didn’t get transcribed is kept to retry. On Android the keyboard keeps recording while you’re in the other app; in Chrome, while you switch tabs. On Android you can also review, copy, export or search any past session.
中文 and English in the same sentence
A language count says nothing about the hard case: an English framework name in the middle of a Chinese sentence. Shuovo is built and tested for English and Chinese, including both at once. “这个 design partner 愿意先给反馈” comes back exactly like that — the English stays English, the jargon stays jargon. No mode button, no language toggle.

One in three of the founder’s sessions was Chinese or both languages. Other languages run through the same engine and work, but are not tuned. On the Android keyboard, tone-assisted input fixes the occasional mis-heard character in a tap or two.
Talk like a person. Send like an engineer.
No prompt syntax. Think out loud, repeat yourself, contradict the sentence before, correct yourself halfway. When you stop, Shuovo doesn’t hand you the wall of text you said — it hands you the draft you meant: paragraphs, punctuation, the structure you were reaching for. Fewer wrong names and mangled numbers, less to re-read.

The keyboard is the last mile: the draft goes into any text field, and the last few fixes are a tap away — select a phrase and say the change, or delete a stray word in one tap. Nothing is sent until you press send.

Free app — voice has a 14-day free trial

The keyboard is free forever. Voice is $15 / month after the trial, transcription included — sign up here to unlock it. Cancel anytime.

What you’ll need

An email address — we send a sign-in link, no password.
A subscription after the trial — $15 / month, cancel anytime. Checkout asks for a card up front, but nothing is charged until the 14-day trial ends — cancel before then and you pay nothing.

I didn’t build Shuovo because I type slowly. I built it because when I’m debugging with an AI assistant or outlining a spec, in two languages, my fingers can’t keep up with my head — and every dictation tool I tried hung up the moment I paused to look at the screen. In my first five weeks of using it, four in ten seconds of my recordings were silence. That’s where the thinking happens. Shuovo exists so you can think out loud without the tool getting in the way.