Transcription

Transcribing audio and video to text

Mark Vesyoly · founder of Potok · ~9 min

Potok turns speech into text in 33 languages, including English and Russian.

Transcription means turning recorded speech into text. Voice messages and video notes in Telegram are transcribed by Telegram itself (without Premium, a few times a week), while files, meeting recordings and YouTube, VK Video or RuTube links are handled by Potok's Telegram bot @potok_now_bot and its mini app: text, timestamps, speakers, a summary and tasks, 60 minutes per month for free.

A recorded interview, lecture, call or long voice message is easier to read than to listen to again: transcription turns speech into text that you can search, quote and forward. Which method to choose depends on where the recording is and what you need to get out of it.

All articles in this section, in Russian (81): potok.now/transkribaciya

What to do with which recording

Prices and terms are taken from the services' official websites.
ServicePlatformsFreePricePayment from RussiaWhere speech is recognized
Potok bot and web versionTelegram (@potok_now_bot, mini app inside the bot)60 minutes per month7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscriptionRussian bank cards, rublescloud, servers in Russia; internet required
Telegram voice message transcriptionTelegramwithout Premium, a few transcriptions per week; with Premium, no limit on their number—not disclosedTelegram servers
SaluteSpeech Bot (Sber)Telegramfree; voice messages, audio and video notes—not disclosedSaluteSpeech cloud (Sber)
Speech2Text.ruWeb3 hours on sign-up—not disclosednot disclosed
Audio2TextWeb, Telegram15 minutes per month295 ₽/mo (Basic, 500 minutes); 495 ₽/mo (Standard, 1000 minutes); 1245 ₽/mo (Expert, 5000 minutes)rublesnot disclosed
Kontur.TolkWeb, Windows, macOS, iOS, Androidnot disclosed—rublesservers in Russia

How to start transcribing audio to text

  1. A short voice message in Telegram: start with the built-in transcription button; if it is enough, you need nothing else.
  2. Everything else: send or forward the recording to Potok's Telegram bot @potok_now_bot: a short one comes back as text in the chat, a long one as a file.
  3. For a recording with several speakers, turn on timestamps and speaker labels in the bot settings (/settings).
  4. Under the text, press Summary or Tasks and deadlines if you need the main points rather than the whole text.
  5. Upload a file of hundreds of megabytes in the web version: it also has a player where clicking a phrase plays the recording from that point.

When the bot will not fit

A recording in another language works too, the bot understands 100+ languages (the language is detected automatically), but it does not translate. For other languages there are services such as Speech2Text.ru, which states more than 90 languages. The bot does not know the speakers' names, only Speaker 1, Speaker 2. There is no transcription during a call itself: that needs the video calling program's own transcription. The bot is cloud-based: recognition runs on servers in Russia, and it does not work without the internet.

Frequently asked questions

Can I transcribe a recording for free?

Yes: Potok's Telegram bot @potok_now_bot and its web version give 60 minutes of recordings per month for free, and the limit renews on the 1st of each month. Voice messages in Telegram itself are transcribed a few times a week without Premium.

Does the bot transcribe recordings in English?

No. Potok's bot recognizes 100+ languages (the language is detected automatically) and has no translation into other languages.

Where can I upload a large file if it takes long in Telegram?

In the bot's mini app: a file of up to 2 GB is dragged into the browser window, and if the connection drops, the upload resumes from where it stopped. Recordings and access there are shared with the bot.

Transcribing audio and video to text: what to do and what to check?

Transcribing audio and video to text. 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 Transcribing audio and video to text you dictate into the same field where you normally type, so there is no need to switch between apps.

Transcribing audio and video to text: how Potok differs from built-in dictation?

Transcribing audio and video to text. 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 Transcribing audio and video to text you dictate into the same field where you normally type, so there is no need to switch between apps.

Transcribing audio and video to text: does recognition work without an internet connection?

Transcribing audio and video to text. 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 Transcribing audio and video to text 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 Telegram

Related software: terms compared

Terms are taken from the services' official websites.
ServicePlatformsFreePricePayment from RussiaWhere speech is recognized
Potok bot and web versionTelegram (@potok_now_bot, mini app inside the bot)60 minutes per month7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscriptionRussian bank cards, rublescloud, servers in Russia; internet required
Telegram voice message transcriptionTelegramwithout Premium, a few transcriptions per week; with Premium, no limit on their number—not disclosedTelegram servers
SaluteSpeech Bot (Sber)Telegramfree; voice messages, audio and video notes—not disclosedSaluteSpeech cloud (Sber)
Voicy (@voicybot)Telegramfree; on the Wit.ai engine, recordings of up to 50 seconds—not disclosedWit.ai, Yandex SpeechKit or Google Speech; the user chooses the engine
Voix (@RecogMyAudioBot)Telegramvoice messages up to 15 minutes, video up to 6 minutes—not disclosednot disclosed
Voicee (@Voicee_AI_Bot)Telegram, Web45 minutes to start500 ₽/hour of recording (without a package; cheaper with packages)rublesnot disclosed
KolerskyAI Whisper BotTelegramthe first 5 minutes69 ₽/15 minutes; 149 ₽/50 minutes; 490 ₽/200 minutesrublesnot disclosed
Transkribator (@gotranscribeai_bot)Telegram, Max3 transcriptions per month—not disclosednot disclosed

Primary 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.

Mark Vesyoly — founder of Potok. Writes about 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 (in Russian) Comparisons · FAQ · About (in Russian) Free voice input · Voice input for AI chats · Data and Russian privacy law · Voice input on Mac · Bot plans (in Russian) · 14 days of Pro for a review (in Russian)