Skip to main content
POST
The model name of Seed Audio 1.0 in AIReiter is seed_audio_1_0. This model is also commonly searched for as Doubao Seed Audio or Seed Audio API.

Authorizations

string
required
All endpoints require Bearer Token authentication.Get the API Key:Visit API Key Management Page to get your API Key.When using it, add the following to the request headers:

Body

string
required
Model name, fixed value:
  • seed_audio_1_0
object
required
Model parameters object.
string
required
Initiator task ID.A user-defined task identifier, required. Only letters, numbers, underscores, and hyphens are supported, with a length of 1-64 characters. You can use this ID later to query the task status and results.

Response

string
The caller’s task ID, which can be used to query the result.
string
The initial status, usually "pending".
string
Creation time, in ISO format.

Query Task

Seed Audio 1.0 is an asynchronous audio generation model. After submitting a task, use out_task_id to query the task status.
string
required
The initiator’s task ID passed when submitting the task.
After the query succeeds and is completed, example output:

Request Examples

Mode Notes

The text mode only generates speech, dialogue, or sound effects based on the prompt; the audio mode clones the timbre using a reference audio; the image mode uses a reference image to guide the expression.
When reference_mode is audio, do not pass image_url. When reference_mode is image, do not pass audio_url. Each request can be up to 120 seconds long.