Skip to main content
VMEG Open API lets you automate what users do on vmeg.ai from your own backend: translate and dub video or audio, synthesize speech, clone voices, and translate plain text.
Video/audio translation = translate + dub. The API transcribes speech, translates the script, generates new AI-dubbed audio (and video when applicable), and returns dubbed media files. It is not the same as the text-only translation API.

​
URLs

The interactive Playground sends requests to https://api.vmeg.ai.

​
Authentication

All /openapi/** endpoints require your API Key in the Authorization request header:
Enter the key in the Playground Authorization field to try requests.

​
Scope

List, detail, and delete operations for tasks and materials, and queries for cloned voices, return only data tied to the API Key you authenticate with. You do not pass a project identifier in query parameters or request bodies.

​
Typical translate-and-dub flow

Most integrators start here when localizing video or audio:
1

Upload your file

Finish the full Upload files (materials) flow to get a registered materialId for your video or audio. See Material upload. Do not create a job with a mid-upload materialId.
2

Configure webhook

Set your webhook URL on API Configuration so dubbed results can be delivered when the job finishes.
3

Create translate and dub job

POST /openapi/v1/task/media-translation/create-async — VMEG transcribes, translates, dubs, and renders output. See Create translate and dub job.
4

Receive dubbed media

Your webhook receives CDN URLs for the dubbed video or audio. Poll Query job status if you need a fallback.

​
Endpoint groups

Async create-async endpoints document the Callbacks webhook request body (task-specific data schema) on the same page. Concept guides (idempotency, webhooks, errors, pricing) are under the Guides tab. Product walkthroughs: Media translation, Products overview.