Tasks
Generate speech (siren-1.0-spicy)
Expressive cinematic text-to-speech: breaths, pauses and tone shifts are part of the delivery rather than tags in the text. Billed by the generated audio duration. Async: returns a task (202); poll GET /v1/tasks/{id}.
post/v1/siren-1.0-spicy
Request
- Base URL: https://api.hotapi.ai
- URL: https://api.hotapi.ai/v1/siren-1.0-spicy
- Auth: HTTP bearer
Query parameters
webhookstring uri
Public HTTPS callback URL for the signed terminal task event. Private addresses and redirects are not supported. Deliveries use the organization's webhook signing secret.
Headers
idempotency-keystring
Stable key for one logical submission. Reuse it only when retrying the identical model and input.
Request body
Example request
{
"text": "今天我想告诉你一件事,先别急,让我慢慢说。",
"voice": "Kore"
}Response
An async task. Creation returns 202 with status=queued; poll GET /v1/tasks/{id} (or await the webhook) until a terminal status.
Example response
{
"id": "task_8sd9f7aQ2",
"model": "z-image-spicy",
"task_kind": "image.generate",
"error": {
"type": "provider_error",
"code": "generation_failed",
"message": "Generation failed"
},
"estimated_credits_cost": 26,
"api_key_id": "ak_8sd9f7aQ2"
}Changes
No recorded changes to this operation across all 1 revision of this API.