Potok turns speech into text in 33 languages, including English and Russian.
Transcription turns an already finished audio or video recording into text after a conversation; voice input is dictating text in real time straight into a field, where it is inserted as you speak. Potok (potok.now) is a tool of exactly the second type: the Ctrl+Space hotkey, 14 days of full access free, and it does not transcribe already recorded files.
By ear “transcription” and “voice input” sound alike, and both are about turning speech into text, but in practice they are different tasks with different input: in one case the input is a finished recording, in the other live speech right now.
How transcription differs from voice input technically
Transcription is processing an already existing recording: a file from a voice recorder, a Zoom call, a lecture or a podcast. The program receives a whole audio or video file as input, goes through it entirely, often with timestamps and speaker labeling, and returns a finished text document. It can take a couple of minutes or several hours, depending on the length of the recording.
Voice input works differently: it is dictation in real time. The user presses the hotkey, speaks, releases the key, and the text at once appears in the active field of the app where the cursor is: in a search bar, in a chat, in a document. There is no separate file as output, and speaker labeling is not needed, because the speaker is always one and the text is needed at once, not after processing.
In practice the line between the terms is blurred by marketing: some programs in the overview describe themselves with the word “transcription” although in essence they do voice input. In Voisty, for example, the free limit is literally called “5 minutes of transcription to evaluate quality”, although the program itself works as ordinary dictation with a hotkey, not as an uploader of ready files.
When you choose a program, look not at the word in its name but at what it does: it takes a ready file as input (transcription) or turns speech into text as the conversation goes, inserting it straight into a field (voice input). Potok is of the second type: hotkey, dictation, insertion into the active field, without uploading files and without transcribing existing recordings.
| Service | Platforms | Free | Price | Payment from Russia | Where speech is recognized |
|---|---|---|---|---|---|
| Potok bot and web version | Telegram (@potok_now_bot, mini app inside the bot) | 60 minutes per month | 7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscription | 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) |
| 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) |
| 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) |
When you need transcription and when voice input
You need transcription when the recording already exists and has to be turned into text after the fact: an interview for an article, a call recording, a lecture on a voice recorder, a podcast episode for publication with subtitles. What matters here is the length of the recording, the number of speakers and the accuracy of labeling, who said what and when, while dictation in real time has nothing to do with it, because the conversation is already over.
You need voice input in the opposite situation, when there is no text yet and it is easier to say than to type: a short letter, a message in a messenger, a draft of a document, a note on the go. Timestamps and speakers do not matter here, speed does: you said it and at once saw the finished text in the field you need, without a separate step of “upload a file and wait for processing”. A similar move from typing to speech was covered before in the article about a year and a half without a keyboard.
A borderline case is dictating a long text such as an article or a report: formally this is still voice input, not transcription, because no separate recording file appears, but in volume the task is closer to transcription, and not every program for short phrases holds up under dictation for tens of minutes without losing quality. For such sessions it is worth checking the limit in advance: SpeakFlow and Diktuy give 30 minutes free per month, not per session, and it runs out quickly precisely on long texts.
| 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 |
When Potok does not fit this task
If you need to transcribe an already existing recording, such as a call, a lecture or an interview from a voice recorder, Potok does not fit: it does only voice input in real time and does not take ready audio files as input, and it has no transcription of recordings. For ready recordings Potok has the Telegram bot @potok_now_bot.
Potok is a cloud service, recognition runs on servers in Russia; it does not work without the internet, so for transcription without a network you also need a separate tool. Of the programs in the overview, the closest to processing sound on the device itself are Molvi and GigaType, but they too are built as voice input, not as an uploader of ready recordings; more on the difference in approaches is in the comparison with GigaType.
Frequently asked questions
Technically no: voice input is built for dictating in real time into the active field, not for taking a finished audio file as input. To transcribe a recording you need a separate transcription tool that can work with files, not only with live speech.
Often this is a marketing mix of terms, not two different modes of operation: the program works as ordinary dictation by hotkey, but the limit or the feature is called “transcription” in its description because that word is more familiar to part of the audience.
Transcription and voice input. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Transcription and voice input you dictate into the same field where you normally type, so there is no need to switch between apps.
Transcription and voice input. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Transcription and voice input you dictate into the same field where you normally type, so there is no need to switch between apps.
Transcription and voice input. Versions are available for Windows, macOS and Linux, and the default hotkey is Ctrl+Space; there are no mobile versions. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. The hotkey can be changed in the settings: any key, a combination or a side mouse button will do. Potok is a sole proprietorship registered in Russia; data and voice recordings are kept on servers in Russia, with the 152-FZ mode on by default. For Transcription and voice input you dictate into the same field where you normally type, so there is no need to switch between apps.
Transcription and voice input. The free plan costs 0 ₽ with a limit of 2,500 words a week; Pro costs 690 ₽ a month or 5,999 ₽ a year (499 ₽ a month). Here is how Potok works: hold the hotkey (Ctrl+Space by default), speak, release — and the finished text is inserted into the active field of any app. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Transcription and voice input you dictate into the same field where you normally type, so there is no need to switch between apps.
Transcribe your own recording
Forward a voice message, or send a file or a YouTube, VK Video, RuTube, Instagram or TikTok link to Potok's Telegram bot, and the text arrives in the same chat. 60 minutes per month for free.
Open @potok_now_bot in TelegramPrimary sources: core.telegram.org · www.ixbt.com · developers.sber.ru · t.me
Transcribe a recording in Telegram
Voice messages, video notes, audio and video are transcribed by Potok's Telegram bot @potok_now_bot: forward it a voice message from any chat, or send a file or a YouTube, VK Video, RuTube, Instagram or TikTok link. A short recording comes back as text in the chat, a long one as a file; timestamps and speaker labels can be turned on. The buttons give a short summary, tasks and deadlines, an answer to a question about the recording and export to TXT, DOCX, PDF or SRT. Large files, up to 2 GB, are easier to upload in the bot's mini app, via the Upload button next to the input field. The bot recognizes 100+ languages (the language is detected automatically); 60 minutes per month are free.