Potok turns speech into text in 33 languages, including English and Russian.
Meeting notes are made not from memory but from a recording of the conversation: send a file or a link to the Potok bot (potok.now) @potok_now_bot, and it will transcribe the speech, and the “Summary” button will collect the main points and tasks by speaker. Speaker labels and timecodes can be turned on in the settings in advance. Speech in 100+ languages is recognized (the language is detected automatically); 60 minutes per month are free.
After an hour-long meeting, few people have the strength to listen to the recording again and write out who decided what. It is more reliable to build the notes from the transcript text than from memory.
How to record a meeting so that you can make notes later
The quality of the future notes is laid down at the meeting itself:
- record in a single file, with no pauses or restarts, so the transcript does not fall apart into pieces;
- put the phone or voice recorder closer to the speakers, not to a speaker or a window, since background noise drowns out quiet voices;
- if the meeting is in Zoom, Telemost or another calling program, turn on recording right in it: the bot does not join the call itself, it needs a ready file. The difference between such a transcript and ordinary voice input of text is covered in the article “transcription and voice input: what is the difference”;
- if the speakers change during the meeting, keep the order of speeches in mind: the bot tells them apart by the numbers “Speaker 1”, “Speaker 2”, not by names.
How to get meeting notes from a transcript
A sent recording turns into notes in a few presses. First the recording file or a link is forwarded to the Potok bot: a short transcript comes as text right in the chat, a long one is saved as a file. Then under the text there are ready buttons: “Summary” collects the main points and tasks for each speaker, “Tasks and deadlines” separately lists who has to do what and by what deadline, and “Ask” lets you put your own question to the bot about the content of the recording, for example what was decided on a specific agenda item. If the ready buttons are not enough, you can create up to five of your own with a preset prompt, for example a “Minutes” button, into which you write your own wording of the request to the text. If several people took part in the meeting, it is worth turning on speaker labels and timecodes in the bot settings in advance, and then the summary and tasks will show who exactly said what. The bot does not shorten or retell the transcript text itself: punctuation, capital letters and obvious recognition errors are fixed, and the meaning stays as in the recording.
| 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 |
| Google voice input (Google Docs voice typing + Gboard) | Web (Google Docs, Chrome/Edge/Safari, current versions), Android (Gboard), iOS (Gboard) | free, built into Google Docs and the Gboard keyboard | — | not disclosed | cloud: in Google Docs, speech recognition is handled by the browser, which manages the speech-to-text service and determines speech processing, after which the text is sent to Google Docs (that is, a cloud service of the browser or Google is used, not local processing). In Gboard some advanced voice typing features for certain locales run on the device and are not sent to Google servers by default, but ordinary Gboard voice input is generally cloud-based |
| Spokenly | macOS, Windows, Linux, iOS | local models (Whisper/Parakeet) are free forever with no word limit; connecting your own API keys (BYOK) is also free | $9.99/mo (Pro, monthly); $99.99/yr (Pro, yearly (≈$8.33/mo)) | not disclosed | hybrid: locally on the device (Whisper/Parakeet, free) or in the cloud (GPT-4o Transcribe, Deepgram Nova 3, Soniox and others, via BYOK or Pro) |
| A-Golos | macOS, Windows, Android | 20 minutes of audio per month free, no card attached | 490 ₽/mo (Lite, 120 min/mo); 4900 ₽/yr (Lite, yearly); 950 ₽/mo (Pro, 300 min/mo) | rubles directly (through an external payment provider, card data is not stored by the service) | cloud: the policy states that personal data is stored on servers in Russia, but the speech recognition itself is performed by OpenAI (USA); results and audio are not stored on the company's servers |
| v2txt.ru | Windows, macOS | Start plan: 2000 words/week | 0 ₽/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 |
| 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) |
| 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) |
| 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) |
| Aqua Voice | macOS, Windows, iOS | Starter: 1000 free words (Avalon model), no card required | $8/mo (Pro, billed yearly); $10/mo (Pro, monthly); $24/mo (Max, billed yearly) | unknown: the website shows payment in USD, and there is a separate purchase through the iOS App Store; acceptance of Russian cards is not confirmed (not confirmed) | cloud (own Avalon model; the country of the data center is not publicly disclosed) (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) |
| SuperWhisper | macOS, Windows, iOS | free: small local models with no usage limits (offline) | $8.49/mo (Pro, monthly); $84.99/yr (Pro, annual (≈$7.08/mo)); $249.99/one-time (Lifetime, one-time, covers Mac+Windows+iOS) | not disclosed | hybrid: small local models offline (free), large cloud models (Scribe, Nova, Gemini, GPT and others) through the Superwhisper proxy on Pro/BYOK — providers see the request from the proxy, not the user's account |
Where the meeting recording is stored
The audio recording of the meeting and its transcript stay on Potok servers in Russia, not in Telegram itself and not on someone else's server abroad. You can open them again in the My recordings section at any moment, without transcribing again. If the meeting involved personal data or commercial secrets, this is worth considering before sending the recording anywhere: cloud recognition is also a place where the content of a conversation ends up.
When the bot does not fit for notes
A recording in another language works too, the bot understands 100+ languages (the language is detected automatically), but it does not translate. There will be no real names of participants in the notes: they can be told apart only as “Speaker 1” and “Speaker 2”. Recording a meeting on the fly while it is going on will not work either: the bot needs a ready file, not a connection to a current call. The bot accepts links to Instagram (Reels and posts with video) and TikTok, as well as YouTube, VK Video and RuTube. And without the internet the bot does not work: it is cloud-based, recognition runs on Potok servers in Russia and not on the device itself. A broader comparison of transcription services shows options besides the bot if none of the points here fit.
Frequently asked questions
You can create your own button with a ready prompt, for example “Minutes”: you word the prompt yourself, and the bot will apply it to the transcript. The bot has no ready-made minutes buttons by default, only “Summary” and “Tasks and deadlines”.
Meeting notes from a recording. 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 Meeting notes from a recording you dictate into the same field where you normally type, so there is no need to switch between apps.
Meeting notes from a recording. 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 Meeting notes from a recording you dictate into the same field where you normally type, so there is no need to switch between apps.
Meeting notes from a recording. 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 Meeting notes from a recording you dictate into the same field where you normally type, so there is no need to switch between apps.
Meeting notes from a recording. 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 Meeting notes from a recording you dictate into the same field where you normally type, so there is no need to switch between apps.
Download Potok
Works with a single key in any program. 14 days of full access, then Free with 2500 words per week or Pro at 690 ₽/mo (499 ₽/mo paid yearly). Potok is a cloud service, so it does not work without the internet.
Download PotokA voice message from a messenger or a call recording can be forwarded to the bot @potok_now_bot, and it sends back the text. The bot is part of the same subscription as the Potok app.
Primary sources: yandex.ru · vc.ru · speech2text.ru · audio-2-text.ru