Generate speech or sound
generate_audioGenerate speech (text-to-speech) for the title. Billed per character. The voice comes from the tier's model unless you pass one in params. Runs as a job: the call waits up to about two minutes and returns the result; if it is not ready by then it returns the generation with status queued/running — poll get_generation with its id.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The words to say out loud. They are read verbatim, so do not put instructions here. | |
| tier | No | Quality/price tier, e.g. image-cheap or video-premium. Call list_ai_tiers for the current list. Omit it to use this title's default tier. | |
| model | No | Model name, if you insist on a specific one (optional). ⚠ Setting it cancels the tier COMPLETELY — together with its provider and its settings — so params may stop applying. Prefer `tier`. | |
| params | No | Model settings, as declared by the vendor for the chosen tier — for example {"aspect_ratio":"16:9","resolution":"720p","duration":"4"}. Call list_ai_tiers to see which keys this tier accepts, their allowed values and defaults. Values are strings. Unknown keys are ignored rather than rejected. | |
| provider | No | Provider key, if you insist on one (optional). Cancels the tier the same way. | |
| title_id | No | Which game this is for — a label for the report, optional. Credits are always the publisher's, so leaving it out is normal for assets that belong to no game. |