Potok transcribes Russian speech; this site has been translated into English for convenience.
A transcript with speaker separation is the text of a recording where lines are labeled with the numbers of the speakers: Speaker 1, Speaker 2 and so on. In the Potok Telegram bot @potok_now_bot this labeling is turned on in the settings before you forward the recording. The bot does not know the participants' names, only the number and order of voices. Transcription is free for 60 minutes per month.
The technical term for this kind of labeling is diarization: the program does not recognize people by voice, it only works out where the same person is speaking and gives them a number. In the transcript it looks like the labels Speaker 1, Speaker 2 before each line.
How to get speaker separation from your recording
- Open the bot @potok_now_bot in Telegram and press "Start" (/start).
- In the settings, /settings, turn on speaker labeling. By default the bot sends text without it.
- Forward the recording, a voice message, audio, video or a file, and the bot applies the setting at once.
- In the finished text, a label Speaker 1, Speaker 2 and so on appears before each line, according to the number of different voices in the recording.
- If you also need timecodes, time marks of the form [mm:ss], they are turned on in /settings separately from speaker labeling.
Transcript terms: timecodes, speakers, subtitles
- "Speaker 1", "Speaker 2" are the numbers with which the bot labels the lines of different people in a recording; it does not know real names.
- Timecodes are time marks of the form [mm:ss] before a line, showing at which minute of the recording it was said.
- SRT and VTT are subtitle file formats: the same text, but split into short lines with timecodes, ready to be laid over video.
- TXT, DOCX, Markdown, PDF are ordinary text formats without timecodes and subtitle markup, for a document or an email.
- Diarization is the technical term for separating a recording by voices; in the bot's interface it is the "Speaker 1", "Speaker 2" labeling.
- "Summary" and "Tasks and deadlines" are buttons under the finished text: the first shortens the recording to the main points, the second gathers from the lines who has to do what.
A broader overview of transcription services is in the article comparison of audio-to-text transcription services.
When the bot will not fit
The bot will not fit if you need the real names of the participants instead of numbers: it does not know them and does not fill them in. Speaker labeling will not work on a recording that is not in Russian either, since the bot recognizes only Russian speech. Voices are separated only after the recording has been sent, not during a conversation in real time. The bot also will not accept a link to Instagram or TikTok: from external sources it understands only YouTube, VK Video and RuTube. The difference between transcribing a finished recording and dictating your own text is covered in the article on transcription and voice input in practice. And without the internet there will be no labeling: the bot is cloud-based, recognition runs on servers in Russia, and it does not work without the internet.
Frequently asked questions
Diarization is separating a recording by voices: the program works out where the same person is speaking and gives them a number. In the Potok bot this looks like the labels Speaker 1, Speaker 2 before the lines.
No. The Potok bot does not know the real names of the speakers and labels lines only with numbers. You can put names in place of the numbers only by hand in the finished text.
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.
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).
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.
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.
Try it on your own recording
Potok's Telegram bot transcribes a voice message, video note, audio or video, and its buttons make a summary and a task list. 60 minutes per month for 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.