from 24 GBChat
Private ChatGPT · Qwen3 32B
A chat in your browser for writing, code and documents. No subscriptions and no message limits.
from €0.30/h · RTX 3090, 24 GB
Ready-made app · Text to speech
AI text to speech on a rented GPU
An affordable 12 GB card is enough for text to speech. There are three ready-made apps: Qwen3-TTS with ready-made voices, VoxCPM2 with lively intonation in 30 languages, and Chatterbox, which speaks in your voice from a 5-second recording. The interface opens in your browser.
- App
- Text to speech · Qwen3-TTS
- GPU
- RTX 3060, 12 GB
- Price
- from €0.12/h
To launch, your balance must cover one hour of the machine. You are billed by the minute for actual use. The server installs Text to speech · Qwen3-TTS for you.
from 12 GBof video memory
2–5 minutesuntil the server is up
By the minutebilled from your balance
Gradioopens in your browser
Examples: what went in and what came out
The same texts, voiced in the ready-made app without any processing. Press play to listen.
Qwen3-TTS
More about Qwen3-TTS →- ENvoice: Vivian · RTX 3060 · 13–28 s per phrase
Welcome to the product tour. In the next two minutes you'll learn how to launch your first GPU server, connect to it, and run a model. No setup required. Let's get started.
- ENvoice: Vivian · RTX 3060 · 13–28 s per phrase
Once upon a time, in a small village by the sea, there lived an old lighthouse keeper who knew every star by name. Each night he climbed the stairs and told the sky a new story.
Launch Qwen3-TTS · from €0.12/h RTX 3060, 12 GB · billed by the minute
VoxCPM2
More about VoxCPM2 →- EN
Welcome to the product tour. In the next two minutes you'll learn how to launch your first GPU server, connect to it, and run a model. No setup required. Let's get started.
- EN
Once upon a time, in a small village by the sea, there lived an old lighthouse keeper who knew every star by name. Each night he climbed the stairs and told the sky a new story.
Launch VoxCPM2 · from €0.12/h RTX 3060, 12 GB · billed by the minute
Chatterbox
More about Chatterbox →- ENdefault voice for the language · RTX 3060 · 5–18 s per phrase
Welcome to the product tour. In the next two minutes you'll learn how to launch your first GPU server, connect to it, and run a model. No setup required. Let's get started.
- ENdefault voice for the language · RTX 3060 · 5–18 s per phrase
Once upon a time, in a small village by the sea, there lived an old lighthouse keeper who knew every star by name. Each night he climbed the stairs and told the sky a new story.
Launch Chatterbox · from €0.12/h RTX 3060, 12 GB · billed by the minute
What is on the server after launch
All three install themselves and run on a 12 GB card. Qwen3-TTS is the simplest, VoxCPM2 sounds the most natural, Chatterbox speaks in your voice.
Text to speech · Qwen3-TTS
from 12 GBTurns text into speech in English and other languages, with several ready-made voices.
- Web interface in your browser
- Qwen3-TTS 1.7B CustomVoice, Apache 2.0 licence
from €0.12/h · RTX 3060 Launch Qwen3-TTS
Text to speech · VoxCPM2
from 12 GBSpeech in 30 languages with natural intonation. Describe a voice in words or clone one from a sample.
- Web interface in your browser
- VoxCPM2, Apache 2.0 licence
from €0.12/h · RTX 3060 Launch VoxCPM2
Text to speech · Chatterbox
from 12 GBSpeech in your own voice from a 5-second recording. 23 languages.
- Web interface in your browser
- Chatterbox Multilingual, MIT licence
from €0.12/h · RTX 3060 Launch Chatterbox
Licence Qwen3-TTS and VoxCPM2 are under Apache 2.0, Chatterbox under MIT: you can use the speech commercially.
How much memory you need and which GPU to pick
Text to speech · Qwen3-TTS needs a card with at least 12 GB; the cheapest suitable one is the RTX 3060. The table shows memory for other versions and tasks. Prices update from available catalogue machines when you open the page.
| Version | Video memoryMemory | Suitable GPUGPU | Price per hourPer hour |
|---|---|---|---|
| Qwen3-TTS 1.7B | from 12 GB | RTX 3060 | €0.12 |
| VoxCPM2 | from 12 GB | RTX 3060 | €0.12 |
| Chatterbox Multilingual | from 12 GB | RTX 3060 | €0.12 |
Guide from real launches: complex graphs and high resolutions need more memory. Pick: the cheapest single card with enough memory. All GPUs and prices
How to run text to speech in 3 steps
- Sign up and top up. Create an account and top up from €10. To launch, your balance must cover at least one hour of the chosen machine; after that you pay by the minute.
- Launch the app. Click Launch Qwen3-TTS. The dashboard opens with Text to speech · Qwen3-TTS and a card with at least 12 GB already selected; check the price and confirm.
- Work in your browser. The server starts in 2–5 minutes, and the app downloads the model in a few more. Then press the Gradio button in the dashboard and type your prompt.
Finished? Stop the server in the dashboard and billing stops. Save and stop keeps /workspace for €0.03 per GB per month, and it comes back on your next server automatically.
Commands for a manual install on an empty server
Qwen3-TTS on an empty server
pip install -U qwen-tts
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --ip 0.0.0.0 --port 7860 --no-flash-attn
What people run text to speech for
01
Voice-overs
Narration for YouTube, Reels and training videos.
02
Voice messages
Delivery notifications, an answering machine, a voice for a bot.
03
Audio versions of texts
An article or a book chapter in audio within minutes.
Tips before you launch
- Voice long texts paragraph by paragraph: it is easier to redo one sentence.
- Write numbers and abbreviations out in words: "ten thousand euros" sounds more natural than "€10,000".
- Only clone your own voice, or a voice whose owner has agreed to it.
Other ready-made apps
Each app installs its interface and model on its own. You only pay for GPU time.
from 24 GBVideo
Video · Wan 2.2 5B
A quick draft of a clip on an affordable card, to test the idea before the final version.
from €0.30/h · RTX 3090, 24 GB
Frequently asked questions
Which text-to-speech app should I choose?
For ready-made voices, Qwen3-TTS is the simplest. If lively intonation matters, take VoxCPM2. For your own voice, Chatterbox. Listen to the samples above: the texts are the same for all three.
Can I voice text in my own voice?
Yes, with Chatterbox and VoxCPM2. A 5–10 second recording without music or noise is enough.
How long does a launch take?
The server usually starts in 2–5 minutes. Then the app downloads the model on its own, which takes a few more minutes, and a button that opens Gradio appears in the dashboard.
What happens to my models and results after I stop?
When you stop, click Save and stop: the /workspace folder with your models, LoRAs and results goes to storage for €0.03 per GB per month and comes back on your next server automatically. If you stop without saving, the disk is deleted.
How is it billed?
By the minute from your balance in euros. Top up from €10; to launch, your balance must cover at least one hour of the chosen machine. Stop the server and billing stops.
A server is usually ready in 2–5 minutes
Sign up in a minute, top up from €10, pay by the minute. Stop the server and billing stops.