Transcription

Meeting transcription into text: how to get the finished text

Mark Vesyoly · founder of Potok · ~9 min

Potok transcribes Russian speech; this site has been translated into English for convenience.

You can transcribe a meeting recording into text with the Potok bot [@potok_now_bot](https://t.me/potok_now_bot) or the web version of the Potok bot: send the finished file or forward the recording from a chat, and you get text labeled by lines, not a general retelling. 60 minutes per month are free, and for long meetings the web version with file uploads of up to 2 GB is more convenient.

The meeting recording has long been ready, but you really do not want to transcribe it by hand, listening and typing across several voices? There is a more convenient way: send the file to the bot or the web version, and the text arrives ready, labeled with who said what.

Where to look for the meeting recording itself

Before transcribing, you need to find the recording in one of the usual forms:

  1. A finished file, audio or video in any common format, saved on a computer or phone after the call.
  2. A voice message or audio file forwarded in Telegram, if the recording is discussed or stored right in the messenger.
  3. A link to a recording that has already been posted, on YouTube, VK Video or RuTube, if the meeting was published as a separate video.

You do not need to convert the format in advance: both the bot and the web version accept a file, a forwarded message or a link without conversion.

How to transcribe a meeting recording into text

  1. Forward the file or voice message to the bot @potok_now_bot in Telegram, or upload it to the bot's mini app by dragging it in (up to 2 GB) or with a link to a video.
  2. If several people spoke at the meeting, turn on speaker labeling in advance: in the bot it is in the /settings, in the web version it is in the recording card. In the finished text the lines will be labeled Speaker 1, Speaker 2 and so on.
  3. Wait for the answer: a short recording comes as text right in the chat, a long one as a separate file, TXT or DOCX.
  4. Under the text there are buttons "Summary" (the main points and tasks for each speaker) and "Tasks and deadlines", so you do not have to reread the whole transcript to find who has to do what.

What a transcript of an ordinary audio file, not a meeting with several voices, looks like is shown in the material on turning an audio file into text on a computer for free.

Transcription right in the call program

If the meeting was held in Kontur.Talk, a Russian video meeting service, it has its own transcription: it is built into the service itself, runs on servers in Russia and supports Russian, and there is no need to forward the recording anywhere.

For meetings in other call programs, first look at their recording settings: if a finished transcript is produced right there, you will not need a separate service at all. If there is no such feature, the recording file and one of the ways above will come in handy.

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
Otter.aiWeb, iOS, Android, Chrome extension, Desktop (Mac/Windows), integrations with Zoom, Microsoft Teams, Google MeetBasic: 300 minutes of transcription per month, up to 30 minutes per meeting, 3 imported files over the whole lifetime of the account, free forever$16.99/mo (Pro, monthly billing, 1200 min/mo); $8.33/mo (Pro, billed yearly (the full year is charged at once)); $30/mo (Business, monthly billing)not directly: dollar billing through international payment processors declines cards issued in Russia and Belarus (confirmed by independent Russian-language guides on dtf.ru and vc.ru; no official Otter.ai statement about blocking Russia was found, this follows from general payment system restrictions)cloud, US servers (the company is registered in the USA); the exact data center is not disclosed on the pricing page
TranskriptorWeb10 minutes on sign-up, limited to 2 min/day (according to the localized Russian site transkriptor.ru); the international site transkriptor.com states a free trial (up to 90 minutes according to secondary sources; the official pricing page could not be opened directly because it timed out)490 ₽/one-time (Start, 150 minutes (transkriptor.ru)); 790 ₽/one-time (Pro, 700 minutes (transkriptor.ru)); 1900 ₽/one-time (Premium, 2100 minutes (transkriptor.ru))yes, on the localized site transkriptor.ru: Visa/Mastercard/Mir bank cards with no fee, SBP via QR code with no fee, YooMoney with a 3% fee; payments are one-off (no subscription) and processed by the KASSA service. The international site transkriptor.com presumably bills in dollars; this is not confirmed directly (the pricing page timed out)not disclosed
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
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
Voix (@RecogMyAudioBot)Telegramvoice messages up to 15 minutes, video up to 6 minutes—not disclosednot disclosed
Telegram voice message transcriptionTelegramwithout Premium, a few transcriptions per week; with Premium, no limit on their number—not disclosedTelegram servers
Speech2Text.ruWeb3 hours on sign-up—not disclosednot disclosed
Prices are taken from the services' official websites.
ServiceFreePaid
Potok bot and web version60 minutes per month7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscription
Otter.aiBasic: 300 minutes of transcription per month, up to 30 minutes per meeting, 3 imported files over the whole lifetime of the account, free forever$16.99/mo (Pro, monthly billing, 1200 min/mo); $8.33/mo (Pro, billed yearly (the full year is charged at once)); $30/mo (Business, monthly billing)
Transkriptor10 minutes on sign-up, limited to 2 min/day (according to the localized Russian site transkriptor.ru); the international site transkriptor.com states a free trial (up to 90 minutes according to secondary sources; the official pricing page could not be opened directly because it timed out)490 ₽/one-time (Start, 150 minutes (transkriptor.ru)); 790 ₽/one-time (Pro, 700 minutes (transkriptor.ru)); 1900 ₽/one-time (Premium, 2100 minutes (transkriptor.ru))
SaluteSpeech Bot (Sber)free; voice messages, audio and video notes—
Voicy (@voicybot)free; on the Wit.ai engine, recordings of up to 50 seconds—
Voicee (@Voicee_AI_Bot)45 minutes to start500 ₽/hour of recording (without a package; cheaper with packages)
KolerskyAI Whisper Botthe first 5 minutes69 ₽/15 minutes; 149 ₽/50 minutes; 490 ₽/200 minutes
Calculated from average typing and speaking speeds, not measured.
TaskCharactersTyping (200 chars/min)Voice (900 chars/min)
chat reply3002 min0.5 min
email15008 min1.7 min
post or meeting minutes400020 min4.4 min
article1000050 min11.1 min

When this will not fit for a meeting

The Potok bot is a cloud service: recognition runs on servers in Russia, and it does not work without the internet. It also will not accept a link to Instagram or TikTok, only Telegram, YouTube, VK Video, RuTube and a whole file.

If the meeting was not in Russian, or you need the text translated into another language, the service will not fit: it recognizes only Russian speech. It tells participants apart by line numbers, not by names. If the minutes must have real names, you will have to write them in by hand. You can compare how different transcription services differ from each other in the comparison of audio-to-text transcription services.

Frequently asked questions

Can I forward a recording to the bot straight from Zoom or Google Meet?

Yes, if the recording is already saved as a file: send it to the bot in Telegram or upload it to the bot's mini app. The bot does not join a call or connect to a conference itself, and works only with a finished recording.

Do I need to state separately who was speaking at the meeting?

No, there is speaker labeling for that: if you turn it on in the settings, the lines in the finished text are labeled Speaker 1, Speaker 2 and so on, by number, without the participants' names.

Can I transcribe a Zoom call automatically?

Yes, a number of platforms have built-in meeting transcription: in Zoom for cloud recordings, in Microsoft Teams during the meeting, in Google Meet on Google Workspace plans. The alternative is to record the sound and process it with a separate transcription service after the call. The Potok app does not do such transcription, since it is for live dictation; you can send a call recording as a file to the Potok Telegram bot @potok_now_bot.

Can I transcribe meeting minutes through voice input?

With Potok you can dictate minutes live, saying them as the meeting goes on or right after it. Transcribing an already recorded audio file of a meeting (a finished Zoom or Telemost recording) is a separate transcription task: you can send such a file to the Potok Telegram bot @potok_now_bot.

What is the difference between voice input and transcription?

Voice input is dictation in real time: you speak and get text in the active field at once. Transcription is turning an already finished audio or video recording (for example, a recording of a meeting) into text after the fact. The Potok app solves the first task, live dictation; finished recordings in Russian are transcribed by its Telegram bot @potok_now_bot.

How is transcription different from voice input?

Voice input is dictation in real time into an active text field. Transcription is turning an already finished audio or video recording (a lecture, a call, a podcast) into text after the fact, often with diarization (separation by speaker).

Transcribe your own recording

Forward a voice message, or send a file or a YouTube, VK Video or RuTube 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

Primary sources: yandex.ru · vc.ru · speech2text.ru · audio-2-text.ru

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 or RuTube 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 Russian speech; 60 minutes per month are free.

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