Potok turns speech into text in 33 languages, including English and Russian.
A summary and a task list from an audio recording are made by the Potok Telegram bot @potok_now_bot: send a recording, get a transcript, and then the Summary button gives a short retelling and the Tasks and deadlines button shows who must do what and by when. Transcription is free for 60 minutes per month, and you do not need to download the file in advance.
A summary is not the full text of the transcript but a shortened retelling of the recording: the main points and, if there are several speakers, the tasks for each. The Potok bot @potok_now_bot builds it from a ready transcript with one button, with no manual note-taking.
What the bot for a summary of an audio recording can do
From a received recording, the bot makes not only the whole text but also several ready formats:
- Summary: a short retelling of the recording, the main points and, if there are several speakers, the tasks for each of them;
- Tasks and deadlines: a separate list of who must do what and by when, pulled from the content of the conversation;
- Ask: an answer to your own question about the recording, without reading the whole text;
- Other format: switching between text and a file;
- up to five buttons of your own with your own query to the text, which the user sets up, for example "Minutes" or "Letter to the client";
- export to TXT, DOCX, Markdown, PDF, and to the subtitle formats SRT and VTT;
- the same is also available in the bot's mini app, a web version with dragging of a file up to 2 GB and search across your recordings.
All formats support the same sources: voice messages, audio, video, files and links to YouTube, VK Video, RuTube. Exactly how forwarding an ordinary audio file to the bot works is in a separate guide to transcribing audio through a Telegram bot. All versions, the transcript, the summary and the tasks, stay in the My recordings section and can be opened again at any time.
| 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 |
| Glas (LidFly) | Windows, macOS | 0 ₽ — 2000 words per week free for life, no card and no email sign-up; the first 2 weeks have no word limit | — | rubles directly: payment via SBP; invoices for companies and sole proprietors | cloud (Russia) — the site says “Russian servers, works without a VPN” |
| 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) |
| Typeless | Windows, macOS, iOS, Android | 8000 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 stated | cloud (the server country is not officially disclosed; the privacy policy only says 'processed in real time on our cloud servers') (not confirmed) |
| 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) |
| Dragon NaturallySpeaking | Windows | not disclosed | $699.99/one-time (Dragon Professional Individual v16, perpetual licence) | not disclosed | device (offline) — local acoustic engine (~8 GB neural network) after installation; internet is only needed to activate the licence |
| Lispr | Windows, macOS | 60 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.) |
| 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) |
| 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 |
| MacWhisper | macOS | A free version is available ("Free forever", limited functionality), Pro is paid | €64/one-time (Pro, one-time purchase through Gumroad, lifetime updates); $29.99/yr (Pro, App Store version ("Whisper Transcription"), subscription); $99.99/one-time (Pro, App Store version, one-time purchase) | not disclosed | on the device (offline) by default, with local Whisper models; there are optional cloud transcription providers, but not as the main mode |
| 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) |
Who a summary and a task list from a recording suit
A summary and tasks from a recording will be useful if:
- after a meeting you need not the full text but a short list of decisions and owners;
- it is easier to take notes on a lecture or webinar by the main points than to rewatch it whole;
- for an interview or a podcast you need a quick overview of the content before deciding what to use in an article;
- voice notes to yourself have piled up, and it is already hard to remember what is important in them;
- you need to quickly give a colleague the gist of a long conversation without forwarding the original recording whole.
When the bot will not fit
The bot will not fit if the recording is not in Russian: it recognizes 100+ languages (the language is detected automatically), and there is no translation. The summary and tasks are built after the recording has been sent, and not in real time during a conversation. The bot accepts links to Instagram (Reels and posts with video) and TikTok, as well as YouTube, VK Video and RuTube. A broader overview of transcription services is in the article comparison of audio-to-text transcription services. And nothing will work without the internet: the bot is cloud-based, recognition runs on servers in Russia, and it does not work without the internet.
Frequently asked questions
Yes, the Summary button is available within the Potok bot's free limit of 60 minutes of transcription per month, and there is no separate charge for the summary and tasks.
A full transcript is the whole text of the recording. Summary is a short retelling of the main points and, if there are several speakers, the tasks for each of them.
How to get a summary and tasks from an audio 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 How to get a summary and tasks from an audio recording you dictate into the same field where you normally type, so there is no need to switch between apps.
How to get a summary and tasks from an audio 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 How to get a summary and tasks from an audio recording you dictate into the same field where you normally type, so there is no need to switch between apps.
How to get a summary and tasks from an audio 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 How to get a summary and tasks from an audio recording you dictate into the same field where you normally type, so there is no need to switch between apps.
How to get a summary and tasks from an audio 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 How to get a summary and tasks from an audio recording you dictate into the same field where you normally type, so there is no need to switch between apps.
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, so it does not work without the internet.
Download PotokYou 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.
Primary sources: yandex.ru · vc.ru · speech2text.ru · audio-2-text.ru