Skip to content

Overview

Media Studio API Documentation

The Media Studio API exposes a single REST interface for image, video, and audio generation. All endpoints are documented below via interactive Swagger UI — you can explore request/response schemas, try calls directly, and download the OpenAPI spec.

Authentication

Use one of the following headers:

  • X-API-Key: Bearer <API_ACCESS_TOKEN>
  • Authorization: Bearer <JWT>

When using a JWT, the API parses user_id (or sub), client (or aud), and email to enrich usage tracking data stored in Azure Table Storage.

API domains (from OpenAPI)

  • Health
  • Provider Discovery
  • Upload
  • Prompt Generation
  • Media Captioning
  • Image Editing
  • Image Generation
  • Vector Graphics Generation
  • Image Sequence Generation
  • Variation Generation
  • Image Editing Generation
  • Inpainting & Erasing
  • Image Expansion
  • Background Editing Generation
  • Background Generation
  • Image Enhancement & Upscaling
  • Video Editing
  • Video Generation
  • Video Editing Generation
  • Text-To-Speech
  • Sound Effect
  • LoRA Project Management
  • LoRA Training
  • Status

Capability map

flowchart TB
    classDef media fill:#DBEAFE,stroke:#2563EB,color:#1E3A8A;
    classDef audio fill:#FFE4E6,stroke:#BE123C,color:#881337;
    classDef video fill:#DCFCE7,stroke:#16A34A,color:#14532D;
    classDef platform fill:#FDE68A,stroke:#B45309,color:#78350F;

    api["Media Studio API"]:::platform

    api --> img["Image: generation, editing, inpainting"]:::media
    api --> vid["Video: generation, editing"]:::video
    api --> aud["Audio: TTS + SFX"]:::audio
    api --> cap["Captioning + prompt enhancement"]:::media