| title | SpeechInputReferenceImage |
|---|
Reference image. On its own it describes the desired voice (voice design); alongside an input_audio part it is a scene image describing the setting the cloned voice speaks in. At most one per request. Only routed to endpoints that support image references.
| Field | Type | Required | Description |
|---|---|---|---|
image_url |
components.SpeechInputReferenceImageInput | ✅ | Reference image input object |
type |
components.SpeechInputReferenceImageType | ✅ | N/A |