Skip to main content
Use APIXO audio APIs to generate music, synthesize speech, and build voice workflows through the same asynchronous task pattern used by image and video models.
  1. Submit a task with POST /generateTask/{model}.
  2. Poll GET /statusTask/{model} or provide a webhook callback.
  3. Read the final audio URLs from the completed task.

​
Choose an audio model

Compare current USD rates in API Pricing, then read the chosen model’s billing section for charged units, input costs, and minimums.

​
Start building

Generation API overview

Understand the shared async request flow.

MiniMax Speech voice list

Browse supported voice IDs for MiniMax Speech 2.8.

Status Task

Poll for progress, results, and failures.

Webhooks

Receive task completion callbacks.