AI video, image and audio API

A unified AI generation API for developers, with asynchronous video tasks, image generation, and audio and language model workflows.

Build with one OpenAI-compatible API for image, video, audio, and language generation.

AI models and API pricing · Read API docs and request examples

Connect to multiple AI capabilities with one API

  • Video generation: submit text-to-video, image-to-video, and multimodal asynchronous tasks, then poll for results.
  • Image generation: turn text prompts into ready-to-use image results.
  • Audio and language workflows: call audio and language models through the same API surface.

Get started in three steps

  1. Read the API docs, then choose a model and request format.
  2. Use an API key to send a request and save the task ID or generated result.
  3. Poll asynchronous video tasks and read the media URL when they finish.

Docs and prompt resources

Browse the OpenZhenZhen AI Prompt Gallery for reusable image and video prompt ideas. OpenZhenZhen AI Prompt Gallery