Skip to content

Transcribe audio with a Whisper GPU template

Run an audio transcription workload using persistent input and output files.

Published on Oct 12, 2026 | Product: GPU

Before you start

Choose a compatible Whisper template and a model that fits the GPU. Have permission to process the recording.

Steps

  1. Deploy the template and wait for readiness.
  2. Use the displayed application endpoint if the template provides one, or connect over SSH.
  3. Upload or copy a short audio file into the persistent workspace.
  4. Run the transcription using the command or API documented for the image; choose a model and language appropriate for the recording.
  5. Inspect the transcript for accuracy and save it outside the rental before termination. Delete sensitive recordings when no longer required.

Check the result

A transcript is generated and the application uses the assigned GPU where supported.

Troubleshooting

Poor audio, unsupported formats, or an unsuitable language/model can reduce accuracy. A managed transcription API is a separate product path with its own catalog limits and charges.

Last updated October 12, 2026. Availability and prices are shown in the console before checkout.
Still need help? Open a support ticket with your service name, the time of the issue, and a redacted error message. Never include passwords or API keys.
Categories
Billing and support CLI and developer tools DocVault AI GPU Cloud GPU applications Getting started Hosting and DNS Managed AI APIs Object Storage VPS
Products
DocVault AI GPU Object Storage Shared Hosting VPS