Transcription

Transcribe owned audio or video to text and word timings. Upload first, quote, then generate. Language is detected automatically.

Cost

—

ImageProvider: ElevenLabs

Try Transcription in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Create in a project Open in playground Use through API

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation

IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","model":"transcribe","input":{"prompt":"studio portrait of a red corgi, soft light"}}'

Input fields

* required

Field	Type	Default	Allowed
sourceAsset*`sourceAsset` Owned asset:// URI from the upload/import tool. Audio or video with audio; maximum 25 MiB and 60 minutes. Duration is measured by the server.	string	—	string

sourceAsset*sourceAsset

Owned asset:// URI from the upload/import tool. Audio or video with audio; maximum 25 MiB and 60 minutes. Duration is measured by the server.

Type: string
Default: —
Allowed: string

Cost

—

Quote the source asset: existing transcription duration-band pricing applies.

Capabilities

Modesspeech_to_text

Asset slotssourceAsset:audio*

Get API key