Voice messages to text: transcription and dictation

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

“Voice messages to text” means two different tasks: transcribing a voice message you received, or dictating text instead of recording a voice message yourself. Transcribing other people's messages needs a separate transcription service, and for the second task an ordinary dictation program will do: Potok (potok.now), for example, inserts dictated text into the message field of any messenger with a hotkey, at about 900 characters per minute.

People search for “voice messages to text” meaning different things: some need to read instead of listening to a voice message received in Discord, Botim or Element, others want to dictate a message by voice and send it as text, without recording audio at all. The articles below cover both cases for specific messengers.

All articles in this section (80): potok.now/golosovye

The main questions of the topic and where they are answered

Voice messages are annoying: dictating the text right away is often faster than speaking and listening back to a voice message: Potok's dictation speed is about 900 characters per minute.
How to transcribe a voice message in Botim: to transcribe a ready recording you need a transcription tool, for example Voisty with a free 5 minutes of transcription to assess quality.
Dictate text instead of a voice message in Botim: Potok inserts dictated text into the message field after the hotkey.
How to transcribe a voice message in Discord: GigaType recognizes offline through the GigaAM neural network, trained for Russian, without sending the recording to the cloud.
Dictate text instead of a voice message in Discord: an alternative to Potok is Molvi, which is free forever, with no account and no payment.
How to transcribe a voice message in Element (Matrix): WhispeRu also recognizes offline, on the device, but works only on Windows.

Where a beginner should start

Decide what your task is: to transcribe someone else's voice message, or not to record a voice message yourself but dictate text right away. The choice of tool depends on this.
To transcribe messages already received, choose a separate file transcription service: a dictation program such as Potok will not help with this, since it recognizes only what is spoken live. For ready recordings Potok has a Telegram bot, @potok_now_bot.
For the second case, dictation instead of recording a voice message, set up a dictation program and a hotkey so that the dictated text goes straight into the message input field of any messenger.
Check where the sound goes during dictation: to a server, as with Potok, or straight to the device, as with GigaType or Molvi. This is especially important for personal correspondence.
Compare the free limits before paying: Potok has 2500 words per week with no card, Diktuy and SpeakFlow have 30 minutes per month.

Where Potok does not fit

Potok does not fit for transcribing voice messages already received: it recognizes only what is spoken live while the hotkey is held, not ready audio recordings. For ready recordings Potok has a Telegram bot, @potok_now_bot. Potok is a cloud service, recognition runs on servers in Russia, and it does not work without the internet. If you need offline transcription of personal correspondence, look at programs such as GigaType or Molvi, which recognize right on the device.

Frequently asked questions

Can Potok transcribe voice messages that were already sent?

No: Potok recognizes only what is said live while the hotkey is held, and does not work with ready audio recordings. To transcribe voice messages you received, you need a separate transcription service.

Which is faster: dictating text or recording and sending a voice message?

If the recipient finds it easier to read, dictating the text right away is often faster: Potok's dictation speed is about 900 characters per minute, and neither the sender nor the recipient needs to listen to the recording afterwards.

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.

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.

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.

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 Telegram

Related software: terms compared

Terms are taken from the services' official websites.
Service	Platforms	Free	Price	Payment from Russia	Where speech is recognized
Potok bot and web version	Telegram (@potok_now_bot, mini app inside the bot)	60 minutes per month	7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscription	Russian bank cards, rubles	cloud, servers in Russia; internet required
Telegram voice message transcription	Telegram	without Premium, a few transcriptions per week; with Premium, no limit on their number	—	not disclosed	Telegram servers
SaluteSpeech Bot (Sber)	Telegram	free; voice messages, audio and video notes	—	not disclosed	SaluteSpeech cloud (Sber)
Voicy (@voicybot)	Telegram	free; on the Wit.ai engine, recordings of up to 50 seconds	—	not disclosed	Wit.ai, Yandex SpeechKit or Google Speech; the user chooses the engine
Voix (@RecogMyAudioBot)	Telegram	voice messages up to 15 minutes, video up to 6 minutes	—	not disclosed	not disclosed
Voicee (@Voicee_AI_Bot)	Telegram, Web	45 minutes to start	500 ₽/hour of recording (without a package; cheaper with packages)	rubles	not disclosed
KolerskyAI Whisper Bot	Telegram	the first 5 minutes	69 ₽/15 minutes; 149 ₽/50 minutes; 490 ₽/200 minutes	rubles	not disclosed
Transkribator (@gotranscribeai_bot)	Telegram, Max	3 transcriptions per month	—	not disclosed	not disclosed

Built-in dictation and Potok

Based on Microsoft and Apple help pages.
Tool	Where it works	Russian language	Where speech is recognized
Windows voice typing (Win+H)	Windows 10 and 11	Windows 11 only	Microsoft cloud, does not work offline
macOS Dictation	macOS	yes	on the device or on Apple servers
Potok	Windows, macOS, Linux	primary language	cloud, servers in Russia, does not work offline

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.