vust

Text to Speech

Text You'd Rather Say Out Loud.

Paste up to 1000 characters into @vustVoiceBot, pick a voice once with /voices, and get back an audio file you can forward anywhere in Telegram. No install, no account, no studio to learn — 3 generations a day are free.

3 free/day · then $0.10 each · 24+ languages auto-detectedPreview-tier TTS · no voice cloning
Open @vustVoiceBot in Telegram
Audio file, forward anywhere24+ languages auto-detected3 free/day · then $0.10 each

Honest scope

An audio file, not a voice-bubble — and no cloning

@vustVoiceBot delivers a WAV audio file via Telegram's standard audio message, not the round voice-bubble player — native OGG/Opus voice bubbles are a future addition, not in this version. There's no voice-cloning feature either: you pick from 4 built-in presets and 3 speaking styles, nothing more.

The engine is Google's latest preview-generation TTS model — we call it 'preview' because that's what it is, not a broadcast-grade claim.
Specimens

See the difference

Paste text, pick a voice once, forward the result anywhere.

The announcement you'd rather have spoken

The text

"Team, the standup moves to 10am starting Monday — same link, new time. Please update your calendars."

What comes back

The same line as a WAV audio file in the chat, in one of 4 voice presets, ready to forward straight into the team channel instead of retyping it as a pinned message.

A paragraph you'd rather listen to while walking

The text

A 600-character paragraph from an article you saved but haven't had time to sit down and read.

What comes back

One audio clip, generated in the style you last picked with /voices (Warm, Bright, Deep or Bold — Neutral, Warm or Slow-and-clear delivery). Play it on the walk instead of reading it at a desk.

Choosing a voice once

/voices

Pick one of 4 presets and one of 3 speaking styles from an inline keyboard.

What sticks

The choice is saved to your account and reused for every generation after — no need to re-pick each time, just paste text and go.
Practical use cases

Who reaches for VUST Voice

A message you'd rather say than type
An announcement, an apology, a long explanation that reads better spoken
Paste the text, get a WAV audio file back in your chosen voice, forward it wherever it needs to go.
Listening instead of reading
A saved paragraph or article snippet you want to hear on a walk or commute
One audio clip, generated in the voice and style you picked once with /voices and reused every time.
A quick spoken version of an announcement
A team update or notice that needs a human-sounding read, not a wall of text
3 free generations a day cover most one-off needs; after that each clip costs $0.10, stated up front.
How it works01–03

How VUST Voice works

  1. 01

    Paste text (up to 1000 characters)

    Longer text is honestly rejected with a request to split it — never silently cut short.

  2. 02

    Pick a voice once with /voices

    4 presets (Warm, Bright, Deep, Bold) x 3 styles (Neutral, Warm, Slow-and-clear) — the choice is saved and reused.

  3. 03

    Get a WAV audio file back

    Delivered via Telegram's audio-message slot, ready to forward — not a native voice bubble in this version.

Same tool · in Telegram@vustVoiceBot

Paste text, get an audio file

Open @vustVoiceBot, pick a voice once with /voices, and get a forwardable WAV clip. 3 free a day; after that each clip costs $0.10, stated up front.

Open in Telegram
Quality & trust

Honest scope

Audio file, not a voice bubble

Delivery is sendAudio (a WAV file), not Telegram's round voice-bubble player. Native OGG/Opus voice bubbles are a known future gap, not shipped yet.

No voice cloning

4 built-in presets and 3 styles are the full range — there is no feature to clone a specific person's voice.

Preview-tier engine

Google's latest preview-generation TTS model — described honestly as preview-quality, not studio or broadcast-grade.

FAQ

Frequently asked questions

What exactly does @vustVoiceBot send back?

A WAV audio file delivered via Telegram's regular audio-message slot — not the round voice-bubble player. It plays like any audio file and forwards cleanly to other chats. There's no native voice-bubble (OGG/Opus) delivery in this version.

Is there a limit on how much text I can paste in?

Up to 1000 characters per generation. Longer text is honestly rejected with a message asking you to split it into parts — it is never silently cut short, so you never get an audio clip that quietly stops mid-sentence.

Is this voice cloning?

No. There is no voice-cloning feature — you cannot upload a sample and have it speak in someone's voice. You choose from 4 built-in presets (Warm, Bright, Deep, Bold) and 3 speaking styles; that's the full range.

How many languages does it support?

24+ languages are auto-detected directly from the text you paste — there's no manual language picker to fumble with. Write in the language you want spoken and the model reads it in that language.

What does a generation cost?

The first 3 generations each day are free. After that each generation costs $0.10, stated up front, topped up inside Telegram after the exact amount is shown — no subscription and no card required to start. The charge lands the moment you send the text — there is no separate confirmation step — and a failed synthesis or delivery is refunded.

What TTS model is behind this?

Google's latest preview-generation TTS model. We call it what it is — a preview-quality tier, not a studio or broadcast-grade voice engine — because that's the honest description of what you're getting.

Where next

More ways to use VUST Voice

AI voice generatorThe free-tier angle: 3 clips a day, no signup, no studio.Voice vs ElevenLabsChat-native quick clips vs the professional voice studio.Scribe — audio to textThe reverse direction: turn speech into a transcript.All tools

Ready when you are

Text you'd rather say out loud.

No install, no account beyond Telegram, no cloning. Paste text, pick a voice, forward the result anywhere.

Open @vustVoiceBotVoice vs ElevenLabs