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
Run AI models · Whisper
Whisper on a rented GPU: audio transcription
Whisper large-v3 runs on an 8 GB card through faster-whisper; the original version needs about 12 GB. It recognises speech in dozens of languages and transcribes an hour of audio in a few minutes on a GPU, so at volume a rented GPU costs less than cloud speech APIs.
- App
- PyTorch
- 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.
from 6 GBof video memory
2–5 minutesuntil the server is up
By the minutebilled from your balance
SSH and Jupyterserver access
How much memory you need and which GPU to pick
Whisper small / medium runs from 6 GB of video memory; the cheapest suitable card is RTX 3060. Prices update from available catalogue machines when you open the page.
| Version | Video memoryMemory | Suitable GPUGPU | Price per hourPer hour |
|---|---|---|---|
| Whisper small / medium | from 6 GB | RTX 3060 | €0.12 |
| Whisper large-v3 (faster-whisper) | from 8 GB | RTX 3060 | €0.12 |
| Whisper large-v3 (original) | 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 Whisper 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.
- Choose a GPU. Memory for each version is in the table above, and the lightest one runs from 6 GB. The button on this page selects the cheapest option with the PyTorch template.
- Run the model. The server is ready in 2–5 minutes. Open Jupyter in your browser or connect over SSH and run the commands below.
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.
Install and transcribe
pip install faster-whisper
python -c "from faster_whisper import WhisperModel; m=WhisperModel('large-v3', device='cuda'); print([s.text for s in m.transcribe('audio.mp3')[0]])"
What people run Whisper for
01
Interviews and calls
A transcript with timestamps: easy to find quotes and write up meeting notes.
02
Video subtitles
The timestamped segments make an SRT file for YouTube or your video editor.
03
A call archive
Hundreds of sales calls in one rental, then a language model works through the text.
Tips before you launch
- faster-whisper is several times faster than the original and uses less memory.
- For a stream of files, run several processes on one card.
Other ready-made apps
Work through the resulting text in your own chat: the Private ChatGPT app installs Ollama, a Qwen3 model and the Open WebUI chat window. You only pay for GPU time.
from 12 GBChat
Private ChatGPT · Qwen3 8B
A fast chat on an affordable card: email drafts, translations, quick answers.
from €0.12/h · RTX 3060, 12 GB
Frequently asked questions
How much does it cost to transcribe an hour of audio?
An RTX 3090 processes an hour of recording in a few minutes, so a few cents at €0.30 per hour.
How long does a launch take?
The server is usually ready in 2–5 minutes, then SSH and Jupyter are available. Downloading the model depends on its size and is billed as normal server time.
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.