Voice to text in Telegram

Does Telegram have built-in voice-to-text?

Yes, but read the fine print. Telegram's built-in transcription works on voice messages someone sent you. Open a voice note and there's a small transcription icon, an "A", at the edge of the bubble. Tap it and Telegram writes out what the sender said, right under the player. It added this back in late 2023, and it's handy when you can't play audio out loud.

There's a catch worth knowing before you rely on it. Telegram Premium gets unlimited transcriptions; on a free account you get a small number, and then the icon stops obliging until the limit resets. So the built-in feature is real, it's just metered unless you pay for Premium. The transcription also happens on Telegram's side, not on your machine, which matters if the voice note is something private.

But notice what this feature does and doesn't do. It reads back audio that already exists, a recording someone else made. It does not turn your live speech into a message you send. Those are different arrows pointing different ways, and the rest of this guide is about the second one: talking, and getting a typed message out the other end.

Transcribing a voice note vs. dictating a message

This is the distinction everything else hangs on, so let me be plain about it. Transcribing a received voice note is Telegram listening to a recording and writing it down for you. Dictating a message is you speaking and the words appearing in the box, ready to send, no audio attached. One is a reading aid for messages you got; the other is a typing replacement for messages you write.

If all you ever wanted was to read a voice note your friend rambled into, you're done, Telegram's own "A" icon handles it and you don't need anything below. But if you're tired of thumb-typing paragraphs and want to just talk, Telegram has no feature for that. The tool that does it lives outside Telegram: your OS, or a dedicated dictation app. Both are next, in order of effort.

The fastest way: a system-wide hotkey

Here's where a dedicated app changes the math. Whisper by Remskill is not a Telegram bot, a chat integration, or a browser extension. It's a desktop app that works like a keyboard: press a hotkey, speak, and the transcript is pasted at the cursor, in any app, the Telegram compose box included. It works the same in Telegram Desktop and in Telegram open in a browser, because as far as your computer is concerned, you're just typing.

Setup is short:

That's the whole loop. The transcript appears in the compose box, you read it, you press Enter.

Speak, and the message appears in Telegram

Once it's running, the experience is unremarkable in the best way. You put your cursor in the chat, hold the key, talk, let go. A second or so later the text is sitting in Telegram's message box as if you'd typed it. No copy-paste, no separate window, and critically, no voice note for the other person to scrub through, just a normal typed message.

Because the local transcription runs on your machine (pure-Rust, no Python sidecar, no server in the loop), it works offline. Whatever you're dictating never leaves your laptop, which is the opposite of how Telegram's own received-note transcription works, that one runs on Telegram's servers. Windows' own built-in voice typing also needs an internet connection; Whisper's local mode does not.

What the full Whisper app looks like

The hotkey is the part you'll use most, but there's a settings surface behind it. You pick your transcription engine: Whisper models, whose multilingual variants cover 99 languages and the English-only .en builds cover exactly one, or NVIDIA's Parakeet, about 600 MB, 5 to 10 times faster than Whisper on CPU, covering English plus 24 European languages. You set your hotkey, manage history, and save presets. None of that is required to dictate one Telegram message. It's there when you want to tune.

Cleaning up dictated messages with AI

Spoken language is messy. You say "um," you restart sentences, you trail off into a noise that means "you know what I mean." Whisper has an optional AI enhancement step that trims filler and tidies the phrasing before it pastes. So "uh, yeah, so I'll, I'll be there around six, six-ish" becomes "I'll be there around six." Whether that's worth it depends on the chat; a work group, probably, a thread with your sister, probably not.

That cleanup runs locally through Ollama, free, on your own machine. Pro users can route it through the cloud instead, but the filler-cleanup benefit doesn't require Pro; it's there in the free local pipeline. You can also just turn it off and paste the raw transcript, which on a casual chat is often exactly the right call.

Reading voice notes other people sent you

Now back to the first job, because it's the one Telegram actually built. If your real goal is "someone sent me a long voice note and I want to read it instead of listen," you don't need Whisper, or any third-party app at all. Telegram already does this. Open the voice message, tap the small "A" transcription icon, and Telegram writes it out for you.

The one thing to watch is the limit. Free accounts get a capped number of transcriptions; Telegram Premium removes the cap. So if you're transcribing the occasional voice note, the free tier is fine. If a friend communicates exclusively in five-minute audio monologues and you transcribe all of them, you'll hit the wall and either wait it out or upgrade. That's Telegram's call, not something an outside app changes. Reading received notes and dictating your own messages are two separate problems that happen to live in the same app.

When to skip a dictation app and just use your OS

If you only need to dictate the occasional message, don't install anything. Your computer already does this for free. On Windows, press the Windows logo key + H and voice typing opens in any text box, Telegram's chat bar included, with no subscription. On a Mac, the built-in Dictation shortcut (or the mic key) does the same, and on Apple silicon it runs on-device with no internet required. On your phone, the keyboard's microphone icon dictates straight into Telegram's mobile message field; that's iOS or Gboard doing the work, not Telegram, but it works.

The one tradeoff worth knowing: Windows' Win+H needs an internet connection to run, while macOS dictation and Whisper's local mode don't. For a quick "running 5 late, order without me," the OS tool is the right call. Where a dedicated app pulls ahead is volume, the filler cleanup, and dictating offline: the longer and more often you do it, the more those matter.

Pick the smallest tool that solves your problem. For one message, that's the key you already have. For a whole evening of long messages, the dedicated app stops feeling like overkill around the second or third paragraph you didn't have to type.

What Whisper costs

The local dictation pipeline, transcription and the AI cleanup over Ollama, is free for any signed-in user, with no card at signup. So getting your voice into Telegram with Whisper costs nothing. Whisper Pro adds the cloud features (OpenAI transcription, cloud AI enhancement, voice web search), and it carries a separate trial. The exact numbers live on the pricing page rather than here, because prices move and a blog post is a bad place to keep them current.

So there are really three answers to this search, depending on which one you came for. Telegram already transcribes the voice notes you receive, metered unless you pay for Premium. Your computer already dictates short messages for free. And an app exists for when you talk into Telegram all day and the built-in options aren't fast enough. Three tools, two different jobs. Most of the time you need the smallest one that fits.