Errors and fixes

Voice message transcription errors in messengers

Mark Vesyoly · founder of Potok · ~10 min

Potok turns speech into text in 33 languages, including English and Russian.

Discord does not transcribe voice messages at all, Signal deliberately has no such feature, and Telegram has transcription but runs into the free account limit, does not offer it in the desktop version or fails on mixed speech. The error table below helps to sort it out; if you need voice input of text rather than transcription of messages, there are programs such as Potok (potok.now) with a response time of about 0.4 seconds.

A voice message was sent, but nobody read it as text, because the transcription button did not appear, the messenger ran out of its limit, or the messenger did not understand the recording language. Below: which errors are most common in Discord, Signal and Telegram, why they happen, and where to look if the problem is wider than one app.

Why voice message transcription works on and off

Voice message transcription is a separate feature on top of a messenger's main purpose, and developers turn it on in their own way. Discord was built as a voice and text chat for communities and did not add automatic transcription of voice messages: there is simply no such button in the interface. Signal, on the contrary, is built around privacy and encryption: transcription would mean the audio goes to a third-party recognition server, and this contradicts the project's model, so the feature is missing on principle, not temporarily.

Telegram added transcription but built it in as a limited option: on a free account there are few transcriptions per day, and after the limit the button simply does not work. A separate group of errors is not about the limit but about coverage: in the desktop version of Telegram the transcription button may be missing altogether, although it is there on the phone, and recognition gets confused if Russian and English are mixed in one voice message or the recording language is not on the supported list.

In other words, the error is almost never in the device or the network: it is that a specific feature of a specific messenger is built exactly this way. The full comparison of voice input programs shows that similar limitations are common for separate dictation apps too, not only for messengers.

All articles in this section, in Russian (11): potok.now/oshibki/messenger-transcription

When voice input will not help

Potok has nothing to do with the analyses above: it is not transcription of other people's voice messages in a messenger but voice input of text, where you yourself hold the hotkey and dictate into any field. For ready recordings Potok has a Telegram bot, @potok_now_bot. Potok is a cloud service, recognition runs on servers in Russia, so it does not work without the internet. If you need specifically to read a received voice message as text, look for a transcription feature in the messenger itself or use a separate app for transcribing audio files: Potok does not solve this task. For ready recordings Potok has a Telegram bot, @potok_now_bot.

What to read about a specific messenger

Each error is analyzed separately, with checking steps:

The analysis of WhispeRu in the program comparison will be useful if instead of transcribing ready messages you are looking for a way to dictate text yourself.

Frequently asked questions

Why is there no “Transcribe” button on a voice message in Telegram?

Usually it is one of three things: the daily transcription limit on a free account has run out, the message was sent from the desktop version of Telegram, where the button may be missing, or the recording language is not on the supported list, in which case an error about an unavailable language appears instead of text.

Is there a way to transcribe a voice message from Signal?

Not inside Signal: the service deliberately does not send audio to a third-party recognition server, because that contradicts its privacy model. You can read the message as text only by hand, by forwarding the audio file to a separate transcription app, if the recipient agrees.

Voice message transcription errors in messengers: what to do and what to check?

Voice message transcription errors in messengers. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Voice message transcription errors in messengers you dictate into the same field where you normally type, so there is no need to switch between apps.

Voice message transcription errors in messengers: how Potok differs from built-in dictation?

Voice message transcription errors in messengers. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Voice message transcription errors in messengers you dictate into the same field where you normally type, so there is no need to switch between apps.

Voice message transcription errors in messengers: does recognition work without an internet connection?

Voice message transcription errors in messengers. Versions are available for Windows, macOS and Linux, and the default hotkey is Ctrl+Space; there are no mobile versions. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. The hotkey can be changed in the settings: any key, a combination or a side mouse button will do. Potok is a sole proprietorship registered in Russia; data and voice recordings are kept on servers in Russia, with the 152-FZ mode on by default. For Voice message transcription errors in messengers you dictate into the same field where you normally type, so there is no need to switch between apps.

Voice message transcription errors in messengers: how much it costs and what the free plan includes?

Voice message transcription errors in messengers. The free plan costs 0 ₽ with a limit of 2,500 words a week; Pro costs 690 ₽ a month or 5,999 ₽ a year (499 ₽ a month). Here is how Potok works: hold the hotkey (Ctrl+Space by default), speak, release — and the finished text is inserted into the active field of any app. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For Voice message transcription errors in messengers you dictate into the same field where you normally type, so there is no need to switch between apps.

Transcribe your own recording

Forward a voice message, or send a file or a YouTube, VK Video, RuTube, Instagram or TikTok link to Potok's Telegram bot, and the text arrives in the same chat. 60 minutes per month for free.

Open @potok_now_bot in Telegram

Related software: terms compared

Terms are taken from the services' official websites.
ServicePlatformsFreePricePayment from RussiaWhere speech is recognized
Potok bot and web versionTelegram (@potok_now_bot, mini app inside the bot)60 minutes per month7 days: 249 ₽, 30 days: 449 ₽, one year: 2 890 ₽; included in the Potok app subscriptionRussian bank cards, rublescloud, servers in Russia; internet required
SpeakFlowWindows, Web30 minutes of dictation per month, free forever690 ₽/mo (Personal (unlimited))rubles directlycloud (the data center country is not disclosed on the website) (not confirmed)
DiktuyWindows, macOS30 minutes of dictation per month, free forever239 ₽/mo (Profi (monthly equivalent when billed yearly)); 2870 ₽/yr (Profi (year, billed in full)); 479 ₽/mo (Max (monthly equivalent when billed yearly))rubles directly (not confirmed)cloud (the data center country is not disclosed on the website) (not confirmed)
TalkpadmacOS, Windows, Android2500 words/week on desktop, 1500 words/week on mobile, free forever; plus a 14-day Pro trial$6/mo (Pro (billed yearly, $72/yr)); $8/mo (Pro (monthly billing))unknown (not confirmed)cloud (the legal entity is registered in Australia; the website is hosted on Cloudflare; the exact location of the ASR servers is not disclosed in the privacy policy) (not confirmed)
VoistyWindows, macOS5 minutes of transcription (to judge the quality)$6.7/mo (Pro); $67/yr (Pro (year)); $99/one-time (Lifetime)Visa/Mastercard/Amex cards, PayPal; whether Russian cards are accepted is not stated (not confirmed)device (offline, local models such as Whisper Large V3 Turbo / NVIDIA Parakeet)
WhispeRuWindows7-day free trial (no card)290 ₽/mo (monthly license); 1990 ₽/yr (yearly license); 4990 ₽/one-time (lifetime license)rubles directly (payment via YooKassa)device (offline)
GigaTypeWindows, macOSfree with no limits: open source under the MIT license (Copyright (c) 2026 Disrupt Builders), all features are available without payment—not needed: there are no paid plansdevice (offline, Sber's GigaAM neural network)
MolviWindows, macOSfree forever, no accounts and no payment—not needed: the product is free; voluntary donations are accepted via Telegram Tribute or by card on the website, amounts are not fixeddevice (offline; best quality on an NVIDIA GPU, otherwise a fast model on the CPU)

Built-in dictation and Potok

Based on Microsoft and Apple help pages.
ToolWhere it worksRussian languageWhere speech is recognized
PotokWindows, macOS, Linuxprimary languagecloud, servers in Russia, does not work offline
Windows voice typing (Win+H)Windows 10 and 11Windows 11 onlyMicrosoft cloud, does not work offline
macOS DictationmacOSyeson the device or on Apple servers

Primary sources: speakflow.ru · speakflow.ru · speakflow.ru · blog.speakflow.ru

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, RuTube, Instagram or TikTok 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 100+ languages (the language is detected automatically); 60 minutes per month are free.

Mark Vesyoly — founder of Potok. Writes about 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 (in Russian) Comparisons · FAQ · About (in Russian) Free voice input · Voice input for AI chats · Data and Russian privacy law · Voice input on Mac · Bot plans (in Russian) · 14 days of Pro for a review (in Russian)