Skip to content

Transcribe audio with the managed AI API

Submit a supported audio recording to an enabled transcription model and retrieve the result.

Published on Oct 12, 2026

Before you start

Use a catalog-enabled audio model and have permission to process the recording. The currently certified CLI audio path supports files up to 25 MiB and recordings up to 10 minutes; check current catalog limits.

Steps

  1. List models and confirm that the transcription model is enabled.
  2. Prepare a supported audio file within the size and duration limits.
  3. Submit it with a unique idempotency key through the CLI or the documented managed request upload flow.
  4. Wait using the returned request ID rather than re-uploading on a polling timeout.
  5. Read the transcript, verify accuracy against the recording, and review measured-duration billing.

Example

ispeed-ctl models list
ispeed-ctl requests transcribe --file recording.wav --model whisper-tiny-en --idempotency-key audio-example-0001
ispeed-ctl requests wait REQUEST_ID --timeout 10m

Check the result

The request completes with a transcript and actual rounded-duration settlement shown for the operation.

Troubleshooting

Unsupported audio, excessive duration, missing capacity, or insufficient funds can cause rejection. Reusing an idempotency key with different audio is rejected.

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