Potok transcribes Russian speech; this site has been translated into English for convenience.
Voice input for work saves time where there is a lot of text and typing is inconvenient or slow: emails, reports, notes after meetings. Spoken speech comes to about 900 characters per minute against 200 when typing. Potok (potok.now) is one of the tools for this: the Ctrl+Space hotkey, insertion into any work app and 2500 words per week on the free plan.
The work day of a specialist who writes a lot consists of emails, notes after calls and drafts of documents, and all of this takes time that can be cut if typing is replaced by speech. The difference in speed is noticeable: ordinary spoken speech comes to about 900 characters per minute, typing on a keyboard about 200. The materials in this section look at how voice input works in specific professions and scenarios, not only in theory.
How it is used in ordinary work
Voice input in a work context rarely looks the same for different specialists: what a programmer dictates is not like what a doctor dictates between appointments.
Programmers use it differently from what is usually thought: not for writing code line by line, but for prompts and comments in a dialogue with an assistant. Voice input for vibe coding and the work of voice input in Cursor cover this with specific scenarios, and not in the abstract.
For doctors the task is different: filling in an appointment protocol in the MIS (medical information system) between patients, where every extra minute at the computer means a minute stolen from the next appointment. The material on voice input in an MIS covers such a dictation scenario, and there is a separate question: whether recognition systems understand medical terms in Russian at all, without a dictionary and with one.
For lawyers, what comes to the front is not speed but compliance with the requirements of the law: the dictated texts contain names and data of clients, and the checklist on 152-FZ in a law firm covers what to check before trusting this data to a specific service.
Analysts dictate differently: notes and drafts of conclusions between calculations, where capturing a thought quickly matters more than punctuation without errors the first time; the material on voice input for an analyst covers this scenario separately.
All of them share one principle: voice input saves time where there is a lot of text and typing is physically inconvenient or slow, and not where you need to say the same short phrase.
- Voice input in a medical information system: how to dictate an appointment protocol and how it differs from a medical dictation tool
- Voice input for an auditor
- Voice input for a blogger
- Voice input for dyslexia
- Voice input for a marketer
- Voice input in medicine: a review by medical specialty
- Voice input for law: lawyers, advocates, notaries
All articles in this section (269): potok.now/dlya
| Task | Characters | Typing (200 chars/min) | Voice (900 chars/min) |
|---|---|---|---|
| chat reply | 300 | 2 min | 0.5 min |
| 1500 | 8 min | 1.7 min | |
| post or meeting minutes | 4000 | 20 min | 4.4 min |
| article | 10000 | 50 min | 11.1 min |
What to open first
It is easiest to find your way around the section by one criterion: what your profession is, or a task similar in character.
- If your profession is in the list above, start with the material for it: it covers the texts and terms typical for this work.
- If your profession is not there, but the task is similar to someone else's (a lawyer and an HR manager both dictate texts with names and dates), the closest material in meaning will do.
- For comparing specific programs with each other: the section comparison of voice input programs.
- For an option for a team, not for one person: the material on voice input for business.
Who does not need this section
The section will not be useful if the work is not connected with text on a computer at all, or if wording is born slowly, word by word, then there is almost no time gain. It also will not suit where you physically cannot speak aloud: an open-plan office with colleagues nearby, a meeting room during someone else's conversation.
Potok is a cloud service, recognition runs on servers in Russia, and it does not work without the internet: where there is no network or there should not be one, you need a different tool.
Frequently asked questions
It depends on the company requirements. Cloud services like Potok send sound to a server for recognition; for data with special storage requirements you need an option with servers inside the company perimeter, which is provided separately, on request.
A model calculation shows a difference of several times: spoken speech is about 4 times faster than typing. The real saving depends on the volume of text, a particular person’s typing speed and recognition accuracy on professional terms.
Dictation pays off most for long texts written off the cuff: draft emails, notes, replies in messengers, lecture notes, and also when your hands are busy or tired (for example with RSI). For short precise edits (one-word commands, code) typing is often faster.
Potok states about 900 characters per minute by voice against about 200 when typing, roughly 4 times faster. This is the product's own estimate, not an independent measurement.
Voice input is converting speech into text on the fly: the user speaks, and the program transcribes the sound with speech recognition technology (ASR) and inserts the resulting text into the active field: email, messenger, document. In Potok it works through a hotkey: hold it, speak, release, and the text is inserted.
By a model estimate, the average dictation speed through Potok is about 900 characters per minute against about 200 characters per minute when typing normally, so speech is noticeably faster than a 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 PotokThe Potok subscription also includes the Telegram bot @potok_now_bot: forward it a voice message or a long meeting recording and it returns the text. Without a subscription the bot gives 60 minutes per month for free.
Related software: terms compared
| 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) |
Primary sources: speakflow.ru · speakflow.ru · speakflow.ru · blog.speakflow.ru