Voice input in apps: how it works, step by step

Potok transcribes Russian speech; this site has been translated into English for convenience.

Voice input in apps works through a global hotkey that fires in any text field of the active window (email, a document, a messenger) without switching between different tools for different programs. In Potok (potok.now) this is the Ctrl+Space hotkey and a free plan of 2500 words per week: hold, speak, release, and the text lands where the cursor was.

Which app do you use most during the day: email, a messenger, a document editor? Technically the answer changes little: voice input that works at the level of the whole system copes equally well with any of them. The articles in this section cover the nuances of working in specific apps, from work tools such as voice input in Bitrix24 and voice input in Excel to AI chats such as voice input for ChatGPT: where insertion works smoothly and where there are quirks.

The path from installation to habit

Install a voice input program and select Russian explicitly if it supports several languages: the wrong one may be on by default.
Set the hotkey so that it does not clash with key combinations already taken in the apps you use often: in some editors and messengers the standard combinations may be taken by their own functions.
Start with one familiar app, such as email, and dictate a few real emails there rather than test phrases. This shows faster how the program copes with your way of speaking.
Check text insertion in messengers separately from email: message fields sometimes handle inserted text differently, especially if the app has autocomplete or on-the-fly formatting.
Add to the personal dictionary the terms and names that come up often in this particular app: work correspondence and personal messages usually use different vocabulary.
Extend use to a second and third app only after the first one works confidently: this builds a stable habit instead of scattered attempts.
After a few weeks, assess in which apps voice input has taken root and in which you still go back to the keyboard, and work out why.
If an app still has not taken after several attempts, do not force it: go back to the keyboard in that app and keep voice input where it really saves time rather than becoming an extra step.

All articles in this section (52): potok.now/prilozheniya

How to make the habit stick

The habit forms faster with regular use of voice input in the same scenario, without random rare attempts. Start with one recurring task (for example, answering email in the morning) and stick to it for the first week before spreading the habit wider.

At first it helps to keep the keyboard at hand as a fallback: if a phrase is not recognized the first time, it is easier to fix it by hand and keep dictating than to break the flow of speech for another attempt.

Over time you will need this fallback less and less, as the program gets used to your voice and terms and you learn to phrase things so they are easier to recognize.

Where this path will not work

This path does not fit fields where text insertion is technically impossible: passwords, some protected forms of banking services, certain game interfaces in full-screen mode. In such places a voice input program simply has nowhere to insert the finished text, no matter how well it recognizes speech.

Nor will it work where an app requires a specific input format: code, formulas, table data with an exact structure, because the voice conveys connected speech, not symbols line by line. Potok is a cloud service, recognition runs on servers in Russia, and it does not work at all without the internet: where there is no network at all, none of the steps on this path will help. More on whether voice input works in any app and whether Word has voice input is in the neighboring articles of the section.

Frequently asked questions

Does voice input work the same in all apps?

In most text fields, yes, if the app supports standard text insertion. The exceptions are protected fields such as passwords and some specific editors where third-party programs cannot insert text directly.

Do I need to set up voice input separately for each app?

No, if the program works at the system level rather than being built into a specific app. The hotkey is set up once and works the same in email, a messenger and documents, with no re-setup for each program.

Is there voice input on a computer without installing programs?

Yes: Windows has built-in voice typing via Win+H (Russian only in Windows 11, Windows 10 has no Russian; it does not work without the internet), and the Mac has system dictation in the keyboard settings. Both are free.

Does voice input work with any microphone?

Any microphone the system sees as a recording device will do. In Potok you choose it in the app settings or in the tray icon menu; system access to the microphone is required.

What ways of entering text by voice are there besides specialized programs?

Built-in system tools (Win+H in Windows, Dictation in macOS, Voice Typing in Google Docs, Gboard on Android), voice browser extensions, and specialized desktop and web services (Potok and similar) that work on top of any app via a hotkey.

How many characters per minute can you dictate?

By a model estimate, the average dictation speed with Potok is about 900 characters per minute versus about 200 characters per minute with ordinary typing, so speech is noticeably faster than the keyboard.

Check it in one evening

Install Potok, dictate what you usually type and compare. 14 days of full access, no card needed. Potok is a cloud service: speech is recognized on servers in Russia, and it does not work without the internet.

Download Potok

You dictate in the app, and recordings and voice messages are transcribed by @potok_now_bot in Telegram. 60 minutes per month are free; the Potok subscription removes the limit in the bot and in the app.

Related software: terms compared

Terms are taken from the services' official websites.
Service	Platforms	Free	Price	Payment from Russia	Where speech is recognized
Potok	Windows, macOS, Linux	Free: 2500 words per week; full access for the first 14 days, no card needed	Pro 690 ₽/mo, 499 ₽/mo when paid yearly	Russian bank cards, rubles	cloud, servers in Russia; internet required
SpeakFlow	Windows, Web	30 minutes of dictation per month, free forever	690 ₽/mo (Personal (unlimited))	rubles directly	cloud (the data center country is not disclosed on the website) (not confirmed)
Diktuy	Windows, macOS	30 minutes of dictation per month, free forever	239 ₽/mo (Profi (monthly equivalent when billed yearly)); 2870 ₽/yr (Profi (year, billed in full)); 479 ₽/mo (Max (monthly equivalent when billed yearly))	rubles directly (not confirmed)	cloud (the data center country is not disclosed on the website) (not confirmed)
Talkpad	macOS, Windows, Android	2500 words/week on desktop, 1500 words/week on mobile, free forever; plus a 14-day Pro trial	$6/mo (Pro (billed yearly, $72/yr)); $8/mo (Pro (monthly billing))	unknown (not confirmed)	cloud (the legal entity is registered in Australia; the website is hosted on Cloudflare; the exact location of the ASR servers is not disclosed in the privacy policy) (not confirmed)
Voisty	Windows, macOS	5 minutes of transcription (to judge the quality)	$6.7/mo (Pro); $67/yr (Pro (year)); $99/one-time (Lifetime)	Visa/Mastercard/Amex cards, PayPal; whether Russian cards are accepted is not stated (not confirmed)	device (offline, local models such as Whisper Large V3 Turbo / NVIDIA Parakeet)
WhispeRu	Windows	7-day free trial (no card)	290 ₽/mo (monthly license); 1990 ₽/yr (yearly license); 4990 ₽/one-time (lifetime license)	rubles directly (payment via YooKassa)	device (offline)
GigaType	Windows, macOS	free with no limits: open source under the MIT license (Copyright (c) 2026 Disrupt Builders), all features are available without payment	—	not needed: there are no paid plans	device (offline, Sber's GigaAM neural network)
Molvi	Windows, macOS	free forever, no accounts and no payment	—	not needed: the product is free; voluntary donations are accepted via Telegram Tribute or by card on the website, amounts are not fixed	device (offline; best quality on an NVIDIA GPU, otherwise a fast model on the CPU)

Built-in dictation and Potok

Based on Microsoft and Apple help pages.
Tool	Where it works	Russian language	Where speech is recognized
Windows voice typing (Win+H)	Windows 10 and 11	Windows 11 only	Microsoft cloud, does not work offline
macOS Dictation	macOS	yes	on the device or on Apple servers
Potok	Windows, macOS, Linux	primary language	cloud, servers in Russia, does not work offline

Primary sources: speakflow.ru · speakflow.ru · speakflow.ru · blog.speakflow.ru