Transcription

SaluteSpeech Bot: transcribing voice messages in Telegram

Mark Vesyoly · founder of Potok · ~5 min

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

SaluteSpeech Bot is a free Telegram bot from Sber: it recognizes voice messages, audio and video notes in Russian and English, and its description gives no official limit. Telegram itself also has its own transcription: a few times per week without Premium, unlimited with Premium. An alternative for ready recordings is the Potok bot @potok_now_bot: 60 minutes of transcription free per month, with speaker labeling.

A voice message in Telegram can be transcribed right in the messenger, with the built-in button or with one of the bots, which you do not even need to install as a separate app. SaluteSpeech Bot from Sber is one of such bots; below is what it does and when the Potok bot is more convenient instead.

What SaluteSpeech Bot does for transcribing voice messages

SaluteSpeech Bot is a Telegram bot on the SaluteSpeech engine from Sberbank. It transcribes voice messages, ordinary audio files and video notes, recognizes Russian and English speech and works for free: its description gives no official limit on the number or length of recordings. Where the SaluteSpeech servers are physically located is not stated either; all that is known is that recognition is cloud-based.

Telegram itself also has built-in transcription of voice messages and video notes: the button appears right under the message. Without Telegram Premium it can be pressed only a few times per week, with Premium with no limit on the number of transcriptions. For one occasional voice message this may turn out simpler than opening a separate bot.

SaluteSpeech Bot is not the only option among bots for this task; a detailed review of them is in the overview of bots for transcribing voice messages. In Voicy the recognition engine is chosen with the /language command: Wit.ai, Yandex SpeechKit or Google Speech. Voix states 7 languages and accepts voice messages up to 15 minutes for free, and video up to 6 minutes. KolerskyAI Whisper Bot gives only the first 5 minutes free, and after that paid packs of minutes. Transkribator works both in Telegram and in the Max messenger, with 3 transcriptions per month free.

When not to trust a recording to the bot

The Potok bot will not fit if the recording is not in Russian: it has no translation and no recognition of other languages. Transcription during a conversation is also beyond it: it accepts only a ready, finished recording. Participants' names will not appear in the text, only the numbers Speaker 1, Speaker 2. The bot will not accept a link to Instagram or TikTok: of links it takes only YouTube, VK Video and RuTube, and of everything else, files and voice messages. It also will not start without the internet: it is cloud-based, and recognition is computed on Potok's servers in Russia.

Who SaluteSpeech Bot suits

If instead of one voice message you need to transcribe a whole meeting with speaker labeling and the buttons Summary and Tasks and deadlines, the Potok bot @potok_now_bot fits better: 60 minutes of transcription free every month. Other options for such a task are collected in the comparison of transcription services.

Frequently asked questions

Is SaluteSpeech Bot free?

Yes, it is officially free: SaluteSpeech Bot transcribes voice messages, audio and video notes with no announced fee, but the exact limit on the number or length of recordings is not given in its description.

Which languages does SaluteSpeech Bot work in?

Russian and English; this follows from the official description by the developer, SaluteSpeech (Sber).

How is transcription different from voice input?

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).

Can meeting minutes be transcribed through voice input?

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.

Can a Zoom call be transcribed automatically?

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.

What is the difference between voice input and transcription?

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 Telegram

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 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