Omni API
Playground/Speech Toolkit Preview

Run a model

Select a model group and task type, fill the visible inputs, then create a real Omni task.

Current model
Speech Toolkit Preview
audiomock-onlyAudio-minute and character pricing planned

Inputs

Fields are generated from the model catalog.

Upload will run automatically

Choose the required files, then run. Playground will create a draft task, upload through signed storage URLs, and enqueue it.