Transcription API
The Transcription API uses AI to transcribe audio and video content. It converts spoken content into text that you can use for captions, subtitles, repurposing into text posts, or any other text-based workflow.Transcribe Media
Submit an audio or video file for AI transcription.Authentication
This endpoint uses API key authentication. Include your API key in thesoku-api-key header.
An active Soku subscription (trialing or active) is required.
Headers
Rate Limit
10 requests per 60 seconds, in addition to the global tier limit. See Rate Limits.Request Body
Response
Status:200 OK
The
Idempotency-Key is returned as a response header, not in the JSON body.
Examples
Basic transcription
Transcription with idempotency
Use theIdempotency-Key header to prevent duplicate charges if you need to retry a request:
Idempotency-Key, you receive the original result without being charged again.
Transcription with duration estimate
ProvidingdurationSeconds helps the API estimate the credit cost:
Credit Costs
Transcription costs vary based on the duration of the media file. Credits are debited from your account balance when the transcription completes.Monitor your credit balance in the Soku dashboard under Account > Credits. For information on credit pricing and how to purchase more credits, see Credits System.
Idempotency
TheIdempotency-Key header is strongly recommended for transcription requests. Because transcription consumes credits, accidental duplicate requests can result in unnecessary charges.
How it works:
- Include an
Idempotency-Keyheader with a unique value (for example, a UUID) on your first request. - If the request succeeds, the API caches the result keyed by your idempotency key.
- If you retry with the same
Idempotency-Key, the API returns the cached result without processing the transcription again or charging additional credits.
Error Responses
Example error response (insufficient credits):