Voice-over
AI text to speech in Telegram
AI text to speech inside Telegram: paste the text, pick a voice, and take the recording back to the chat. Want your own voice reading it? Clone it once and use it after that.
Read a text aloud12 Stars per week free, no card. That covers a couple of short recordings. What the free allowance covers
Catalogue
Models for voice
Everything running today, with what the cheapest run of each model costs. A subscription never unlocks or locks one of them: you pick.
6 modelsfrom 1 Star
ElevenLabs v3
ElevenLabs at its most expressive: you hear pauses, intonation and emotion instead of a robot. For voiceover and anything a person will listen to end to end.
from 6 Stars
OpenAI TTS
OpenAI's text to speech: an even voice and clear diction, nothing to set up. The plain option for long text, where being understood matters more than acting.
from 1 Star
Grok TTS
Text to speech from xAI, at the cheapest price on the shelf.
from 1 Star
MiniMax Speech 2.8 HD
Studio-grade narration with control over delivery and emotion. It sounds good in Russian.
from 6 Stars
ElevenLabs Flash v2.5
The speed model in the ElevenLabs line: it says short lines cleanly with nothing to configure. Take it for dialogue and reactions, not for half an hour of reading aloud.
from 3 Stars
MiniMax Voice Clone
It takes a voice off a recording and turns it into one you can speak text with. It needs a clean sample, no music and nobody else in the background.
from 178 Stars
How to choose
Which model to pick
Voice splits cleanly into three cases: a short line, a long text somebody will listen to end to end, or your own voice doing the reading.
Short lines and long reads
Grok TTS and OpenAI TTS are the plain readers: even delivery, clear diction, nothing to configure. They are the right call for a long text where being understood beats acting.
1 Star is where a run on those starts, so a free week stretches further here than anywhere else on the site. ElevenLabs Flash v2.5 sits just above them and is built for short lines and reactions.
When someone listens to all of it
ElevenLabs v3 is the expressive one: the pauses, the intonation and the emotion land where a listener expects them, which is what carries a voiceover past its first minute.
MiniMax Speech 2.8 HD is the other studio-grade option and the better pick for Russian, with control over delivery and emotion.
When the voice has to be yours
MiniMax Voice Clone builds a voice out of a recording you send, and any text can be read in it afterwards. It wants a clean sample: no music, nobody talking over you.
The clone is a job of its own with its own price, the largest on this shelf, and you run it once. Reading text with the result is priced like any other voice run.
What Telegram changes
An AI voice generator in Telegram hands the result back as an audio file in the chat you started from, so it forwards to a person or a channel with no download in between.
12 Stars arrive free every week, no card, and they do not roll over: the new week replaces what is left instead of adding to it. Everything past that is paid in Telegram Stars, one credit per Star.
Process
Three steps to a finished recording
- Open the bot@StarGenAI_Bot, and the Mini App from there. Nothing to download.
- Paste the text and pick a voiceThe price updates as you choose and sits on the button before you start.
- Take the recording back to the chatThe audio lands in the same chat you started from. Forward it wherever you like.
FAQ
Questions about voice-over
Is the AI text to speech really free?
You get 12 Stars every week and no card is needed. That covers a short recording, and after that it is either next week's Stars or a top-up. Unused Stars do not carry over.
What does a text-to-speech recording cost?
Every model has its own price, listed above. The same amount sits on the generate button before you start, and that is exactly what is charged: one credit is one Telegram Star.
Can I clone my own voice?
Yes, it is its own model in the list above. It builds the voice once, and after that any text can be read in it.
How does the result arrive?
The finished recording drops into the same chat as an audio file, so you can forward it to a friend or post it to a channel straight away.