Potok transcribes Russian speech; this site has been translated into English for convenience.
Voicy (@voicybot) is a free Telegram bot for transcribing voice messages. By default it runs on the Wit.ai engine, where a recording is limited to 50 seconds, but the engine can be changed with the /language command to Yandex SpeechKit or Google Speech. For longer recordings and whole meetings with a split by speaker there is the Potok bot @potok_now_bot, with 60 minutes of transcription free every month.
Voicy has an unusual feature among Telegram bots for transcription: you can choose the recognition engine yourself instead of getting one ready option. This explains why a short voice message is transcribed while a long one sometimes is not, and when it is simpler to take the Potok bot instead of Voicy.
How Voicy works and why it may not cope with a recording
By default Voicy recognizes voice on the Wit.ai engine, and it has a hard limit: the engine simply will not accept a recording longer than 50 seconds as a whole. Hence the frequent complaint “Voicy does not work”: the cause is usually not a breakdown of the bot but the selected engine. With the /language command inside the bot you can switch to Yandex SpeechKit or Google Speech, but what limits apply to them inside Voicy is not stated anywhere.
The terms of neighboring Telegram bots differ: SaluteSpeech Bot from Sberbank has no official limit in its description at all, but immediately states two languages, Russian and English; Transkribator limits free use to three transcriptions a month, but accepts files in the Max messenger too, not only in Telegram.
A completely different scale is that of web transcription services rather than bots. Otter.ai officially has no Russian recognition: only English and a few other languages, and the bills are in dollars, because of which cards of Russian and Belarusian banks are often declined by international payment systems. Transkriptor, for comparison, has Russian in its list of supported languages, and its Russian version transkriptor.ru takes payment by a Mir card (the Russian payment system) or through SBP (the Russian Faster Payments System) with no commission.
When not to trust a recording to the bot
If the conversation was not in Russian, the Potok bot will not help here: it does not understand other languages and translation. You also cannot wait for the text right during a call: the bot takes only an already finished, saved recording. Instead of the participants' names the reply will have numbers: “Speaker 1”, “Speaker 2” and so on. The bot will not accept links to Instagram and TikTok: of links it understands only YouTube, VK Video and RuTube, and of the rest, files and voice messages. The Potok bot is cloud-based: recognition runs on servers in Russia, and it does not work without the internet.
Who the Voicy bot fits
- those who want to choose the recognition engine themselves: the /language command switches between Wit.ai, Yandex SpeechKit and Google Speech;
- those for whom short voice messages up to 50 seconds on the default engine are enough;
- those who look for a free transcription option right in Telegram without installing apps.
A whole meeting is a different task, not a single voice message: a split by speaker, a compressed summary and a list of tasks from the results of the conversation come in handy there. The Potok bot @potok_now_bot can do this, and for free, 60 minutes of transcription a month; more about it is in the overview of bots for transcribing voice messages. Other bots and services for the same purpose are collected in the comparison of transcription services.
Frequently asked questions
By default Voicy runs on the Wit.ai engine, where a recording is limited to 50 seconds. The engine can be switched with the /language command to Yandex SpeechKit or Google Speech, but what limits apply to them inside Voicy is not stated anywhere.
The bot itself is free: it charges nothing for transcription. The recognition engine inside it is switched with the /language command: Wit.ai, Yandex SpeechKit or Google Speech.
With Potok you can dictate the minutes live, speaking them during or right after the meeting. Transcribing an already recorded audio file of a meeting (a finished Zoom or Telemost recording) is a separate transcription task: such a file can be sent to Potok's Telegram bot @potok_now_bot.
Voice input is real-time dictation into the active text field. Transcription turns an already finished audio or video recording (a lecture, a call, a podcast) into text after the fact, often with diarization (splitting by speaker).
Yes, several platforms have built-in meeting transcription: Zoom for cloud recordings, Microsoft Teams during the meeting, 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 this kind of transcription, it is for live dictation; a call recording can be sent as a file to Potok's Telegram bot @potok_now_bot.
Voice input is real-time dictation: you speak and immediately get text in the active field. Transcription turns an already finished audio or video recording (for example, a meeting recording) into text after the fact. The Potok app handles the first task, live dictation; finished recordings in Russian are transcribed by its Telegram bot @potok_now_bot.
Recording to text
Send a recording to Potok's Telegram bot or upload a file of up to 2 GB in the bot's mini app. The first 60 minutes of every month are free.
Open @potok_now_bot in TelegramPrimary sources: otter.ai · help.otter.ai · transkriptor.ru · support.transkriptor.com
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.