Software

Slow and halting speech: how voice input copes without rushing

Mark Vesyoly · founder of Potok · ~9 min

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

Slow or halting speech with pauses is no obstacle for voice input if recording starts and ends not by a timer but on your command. In Potok (potok.now) the hotkey (Ctrl+Space by default) is held for the whole phrase and released when you have finished; the text comes back with a response of about 0.4 seconds.

Not everyone finds it comfortable to speak fast and without stops: some make pauses to find a word, some speak more slowly than the usual pace. For voice input this should not be a problem, as long as recording is not cut off by a timer but ends when the speaker decides. Let us see how eight voice input programs are built and what to look at if speech is unhurried or halting.

Prices and terms are taken from the services' official websites.
ServicePlatformsFreePricePayment from RussiaWhere speech is recognized
PotokWindows, macOS, LinuxFree: 2500 words per week; full access for the first 14 days, no card neededPro 690 ₽/mo, 499 ₽/mo when paid yearlyRussian bank cards, rublescloud, servers in Russia; internet required
SpeakFlowWindows, Web30 minutes of dictation per month, free forever690 ₽/mo (Personal (unlimited))rubles directlycloud (the data center country is not disclosed on the website) (not confirmed)
DiktuyWindows, macOS30 minutes of dictation per month, free forever239 ₽/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)
TalkpadmacOS, Windows, Android2500 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)
VoistyWindows, macOS5 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)
WhispeRuWindows7-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)
GigaTypeWindows, macOSfree 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 plansdevice (offline, Sber's GigaAM neural network)
MolviWindows, macOSfree 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 fixeddevice (offline; best quality on an NVIDIA GPU, otherwise a fast model on the CPU)
LisprWindows, macOS60 minutes of dictation per week for free; the key features (push-to-talk, translation, dictionary, local history) always stay free, without an account$7.99/mo (Pro, monthly); $79/yr (Pro, yearly (from $44.90 with regional discounts))unknown (not confirmed)cloud (USA; recognition is done by Groq, Inc.)
v2txt.ruWindows, macOSStart plan: 2000 words/week0 ₽/n/a (all of Pro is free until the end of 2026 (the regular Pro/Premium price after 2026 is not published on the website))rubles directly (Visa, Mastercard, Mir cards and T-Bank are accepted)cloud (Russia) in online mode; offline mode processes on the device
TypelessWindows, macOS, iOS, Android8000 words per week (Free plan); new users get a 30-day Pro trial, then move to Free if they do not pay$12/mo (Pro billed yearly (effectively $144/yr)); $30/mo (Pro billed monthly)Visa/Mastercard cards; whether Russian cards are accepted is not statedcloud (the server country is not officially disclosed; the privacy policy only says 'processed in real time on our cloud servers') (not confirmed)

How we selected the programs

For slow and halting speech, what matters most is how the program decides that a phrase has ended: by holding a hotkey that you release yourself, or by a built-in timer and pauses that it guesses automatically. Open product data does not describe this in detail for everyone, so for each program we also looked at the platform, the place where speech is recognized (on the device or in the cloud) and a free plan that is enough to check your own way of speaking before paying. How this feels in practice is in the story of why one user stopped typing by hand.

What stands behind each row of the table

Of the eight programs, details about recording control are in open data for only two: for Potok and for Lispr it is pressing and holding a key, that is, the speaker decides when to start and finish a phrase.

Who fits what

Where Potok does not fit

Potok does not fit if you need to work without the internet: it is a cloud service, speech recognition runs on servers in Russia, and without a network connection the program does not work. Potok has no voice commands for editing already inserted text: if a word was recognized wrongly because of a pause or a stumble, you can correct it only by hand. The free limit of 2500 words per week may also not be enough for someone who dictates a lot and all day, not only in short phrases.

Frequently asked questions

Do I need to speak without stopping for voice input to recognize the text correctly?

No, if the program records while the hotkey is held: pauses inside a phrase do not cut the recording, and the decision of when to finish stays with the speaker, not with the program's timer.

Is there a voice input program with manual control of the start and end of recording?

In Potok and in Lispr recording goes on while the hotkey is held (push-to-talk): you decide yourself when to start and finish a phrase, instead of fitting into the time the program allots.

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.

How much faster is voice input than the keyboard?

Potok states about 900 characters per minute by voice versus about 200 when typing, roughly 4 times faster. This is the product's own estimate, not an independent measurement.

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.

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.

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.

Built-in dictation and Potok

Based on Microsoft and Apple help pages.
ToolWhere it worksRussian languageWhere speech is recognized
Windows voice typing (Win+H)Windows 10 and 11Windows 11 onlyMicrosoft cloud, does not work offline
macOS DictationmacOSyeson the device or on Apple servers
PotokWindows, macOS, Linuxprimary languagecloud, servers in Russia, does not work offline

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

Mark Vesyoly — founder of Potok. Writes about Russian voice input: how to dictate in work apps, what gets in the way and how to fix it.
© Potok · Vladimir Olegovich Lipatnikov · INN 502915859701 · Public offer Comparisons · FAQ · About Free voice input · Voice input for AI chats · Data and Russian privacy law · Voice input on Mac · Bot plans · 14 days of Pro for a review