Skip to main content
POST
/
fish
/
audios
Fish Audios
curl --request POST \
  --url https://api.acedata.cloud/fish/audios \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "action": "speech",
  "prompt": "a white siamese cat",
  "voice_id": "d7900c21663f485ab63ebdb7e5905036",
  "model": "fish-tts",
  "callback_url": "<string>"
}
'
{
  "data": [
    {
      "prompt": "let this man wear on this T-shirt",
      "image_url": "https://platform.cdn.acedata.cloud/nanobanana/8e9e0253-26f4-45b9-b3f8-ac1aed1c284b.png"
    }
  ],
  "success": true,
  "task_id": "93f11baf-347b-4bb4-9520-8653cb46d6a3",
  "trace_id": "a9063166-26ed-4451-85b5-54e896817c69"
}

Authorizations

​
Authorization
string
header
required

API token from https://platform.acedata.cloud

Headers

​
accept
enum<string>

Specifies the format of the response from the server. If not specified, the default format is application/json.

Available options:
application/json

Body

application/json
​
action
enum<string>
required

The act of cloning voices.

Available options:
speech
Example:

"speech"

​
prompt
string
required

The input text information for the task of cloning sounds.

Example:

"a white siamese cat"

​
voice_id
enum<string>
required

When cloning a sound, the voice_id is the basis.

Available options:
d7900c21663f485ab63ebdb7e5905036
Example:

"d7900c21663f485ab63ebdb7e5905036"

​
model
enum<string>

The model adopted for the task of cloning sounds.

Available options:
fish-tts
​
callback_url
string

The callback URL which will be called when the images is generated, the URL should be accessible from the public internet. If specified, the response will be returned immediately and the result will be sent to the callback URL when it's ready.

Response

OK, the request is successful.

The response is of type object.