Skip to main content
POST
/
v4beta
/
model
Fish Audio Audio Cloning
curl --request POST \
  --url https://api.highwayapi.ai/v4beta/model \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "type": {},
  "title": "<string>",
  "train_mode": {},
  "voices": [
    null
  ],
  "visibility": {},
  "description": {},
  "cover_image": {},
  "texts": [
    "<string>"
  ],
  "tags": [
    "<string>"
  ],
  "enhance_audio_quality": true
}
'
{
  "_id": "<string>",
  "type": {},
  "title": "<string>",
  "description": "<string>",
  "cover_image": "<string>",
  "state": {},
  "tags": [
    "<string>"
  ],
  "created_at": {},
  "updated_at": {},
  "visibility": {},
  "like_count": 123,
  "mark_count": 123,
  "shared_count": 123,
  "task_count": 123,
  "author": {
    "_id": "<string>",
    "nickname": "<string>",
    "avatar": "<string>"
  },
  "train_mode": {},
  "samples": [
    {
      "title": "<string>",
      "text": "<string>",
      "task_id": "<string>",
      "audio": "<string>"
    }
  ],
  "languages": [
    "<string>"
  ],
  "lock_visibility": true,
  "unliked": true,
  "liked": true,
  "marked": true
}
The Fish Audio API is used to create voice models (voice cloning).

Request Headers

Content-Type
string
required
Enum value: application/json
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

Request Body

type
enum<string>
required
Model type. tts represents text-to-speech.Available value: ttsAllowed value: "tts"
title
string
required
The model title or name.
train_mode
enum<string>
required
The model training mode. For TTS models, fast means the model is available immediately after creation.Available value: fastAllowed value: "fast"
voices
file[]
required
Upload voice files used to fine-tune the model.
visibility
enum<string>
default:"public"
Model visibility. public will be displayed on the discovery page, unlist allows anyone with the link to access it, and private is visible only to the creator.Available values: public, unlist, private
description
string | null
Model description.
cover_image
file | null
Model cover image. This is required if the model is public.
texts
string[]
Text corresponding to the voices. If not specified, ASR (automatic speech recognition) will be performed on the voices.
tags
string[]
Model tags.
enhance_audio_quality
boolean
default:false
Enhance audio quality.

Response Information

_id
string
required
The unique identifier of the created model.
type
enum<string>
required
Model type.Available values: svc, tts
title
string
required
The model title or name.
description
string
required
Model description.
cover_image
string
required
The URL of the model cover image.
state
enum<string>
required
The current state of the model.Available values: created, training, trained, failed
tags
string[]
required
Model tags.
created_at
string<date-time>
required
The timestamp when the model was created.
updated_at
string<date-time>
required
The timestamp when the model was last updated.
visibility
enum<string>
required
The model visibility setting.Available values: public, unlist, private
like_count
integer
required
The number of likes the model has received.
mark_count
integer
required
The number of favorites/bookmarks the model has received.
shared_count
integer
required
The number of times the model has been shared.
task_count
integer
required
The number of tasks associated with the model.
author
AuthorEntity · object
required
Information about the model author.
train_mode
enum<string>
default:"full"
The training mode used by the model.Available values: fast, full
samples
SampleEntity · object[]
Sample data associated with the model.
languages
string[]
Languages supported by the model.
lock_visibility
boolean
default:false
Whether the visibility setting is locked.
unliked
boolean
default:false
Whether the current user has unliked this model.
liked
boolean
default:false
Whether the current user has liked this model.
marked
boolean
default:false
Whether the current user has favorited/bookmarked this model.