How to turn a WhatsApp voice message into text

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

The Potok Telegram bot @potok_now_bot transcribes a WhatsApp voice message into text: save the recording as a file, send it to the bot in a private chat, and it returns the text. A short recording comes back as text right away, a long one as a file. 60 minutes of recognition per month are free. The bot recognizes only Russian speech, and there is no translation.

A WhatsApp voice message can be turned into text with a third-party tool. The fastest way is the Potok Telegram bot @potok_now_bot: it takes an already saved recording and sends the transcript to the chat. You can send the file directly in a private chat, and nothing extra needs to be installed.

A WhatsApp voice message to text, step by step

The path to the finished text is short: first the recording is saved as a file, then it is sent to the bot.

1. Save the voice message as an audio file. This can usually be done with the tools of the app where you received it.
2. Open Telegram and find the bot @potok_now_bot in search.
3. Press Start (the /start command) if you are writing to the bot for the first time.
4. Send it the saved file in a private chat, as an attachment, as an ordinary document or audio.
5. Wait for the reply: a short recording comes as text right in the chat, a longer one as a separate file.
6. The file format (TXT or DOCX), timecodes and speaker labels can be set with the /settings command even before you send the recording.

What comes back

• the bot sends the finished text of a short recording right away in the same chat message;
• it sends a long transcript as a separate file, TXT or DOCX, depending on what was chosen in advance;
• the Summary button collects the main points of the recording and distributes tasks among the participants of the conversation;
• the Tasks and deadlines button pulls out of the text separately who must do what and when;
• the Ask button answers a specific question about the content of the recording without retelling all of it;
• the Other format button gives the same text in Markdown, PDF or in the subtitle files SRT and VTT;
• when there are several voices and labeling is on, the lines are marked not with names but with numbers: "Speaker 1", "Speaker 2".

The difference between such a transcript and ordinary voice input of text is explained on the page transcription and voice input: what is the difference.

When the bot will not fit

If the recording is not in Russian, the Potok bot will not help: there is only one recognition language, and it does not translate into others. It also will not insert the real names of the participants of the conversation, only the numbers "Speaker 1" and "Speaker 2" instead. The bot does not produce text right during a conversation: it needs an already finished recording sent as a file. It will not accept a link to a video from Instagram or TikTok. Of the video platforms, YouTube, VK Video and RuTube are supported, plus direct files. A broader overview of transcription services is in the comparison of transcription services. The bot itself is a cloud service: it does not work without internet access, and voice is processed on servers in Russia.

Frequently asked questions

Primary sources: core.telegram.org · www.ixbt.com · developers.sber.ru · t.me