Run Whisper on RTX 3090 — Quick Start

Deploy OpenAI Whisper (including Large v3) on a dedicated NVIDIA RTX 3090 (24GB) and call the transcription API.

1) Choose minutes & pay

Go to Whisper on GPU, choose minutes, and pay in INR (Razorpay) or USD (PayPal/cards).

2) Receive your endpoint

If the GPU is free we deploy immediately; otherwise we queue and email you the live URL + token.

3) Example request

POST https://<your-endpoint>/api/whisper/transcribe
Authorization: Bearer <token>
Content-Type: multipart/form-data

file=@audio.wav
model=large-v3
language=en

Tip: Use 16 kHz mono WAV for speed and accuracy.

Also see: SDLS hosting · LLM hosting.