Skip to main content
POST
  • Create: POST /v1/tasks/autodl with model indextts-2
  • Poll: GET /v1/tasks/{task_id} (fetch output audio through GET /v1/tasks/{task_id}/artifacts)
  • Dedicated workflow channel supporting reference voice clone and emotional nuance control
  • Recommended: For 3-second instant generation, prefer official mainstream seed-audio-1.0 voice clone mode

Identity

Endpoint

Base URL: https://api.omnimux.ai

Authorizations

Body

Response

200 (Create)

Poll & Artifacts

After completion, fetch the synthesized WAV audio through GET /v1/tasks/{task_id}/artifacts.