> ## Documentation Index
> Fetch the complete documentation index at: https://docs.novita.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Fish Audio Voice Cloning

Fish Audio API for creating a voice model (voice cloning).

## Request Headers

**Content-Type** `string` *required*

Enum: `application/json`

**Authorization** `string` *required*

Bearer authentication format, for example: Bearer \{\{API Key}}.

## Request Body

**type** `enum\<string\>` *required*

Model type, tts is for text to speech.

Available options: `tts`

Allowed value: `"tts"`

**title** `string` *required*

Model title or name.

**train\_mode** `enum\<string\>` *required*

Model train mode, for TTS model, fast means model instantly available after creation.

Available options: `fast`

Allowed value: `"fast"`

**voices** `file[]` *required*

Upload voices files that will be used to tune the model.

**visibility** `enum\<string\>` (default: public)

Model visibility, public will be shown in the discovery page, unlist allows anyone with the link to access, private only be visible to the creator.

Available options: `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[]`

Texts corresponding to the voices, if unspecified, ASR will be performed on the voices.

**tags** `string[]`

Model tags.

**enhance\_audio\_quality** `boolean` (default: false)

Enhance audio quality.

## Response

**\_id** `string` *required*

Unique identifier for the created model.

**type** `enum\<string\>` *required*

Model type.

Available options: `svc`, `tts`

**title** `string` *required*

Model title or name.

**description** `string` *required*

Model description.

**cover\_image** `string` *required*

URL of the model cover image.

**state** `enum\<string\>` *required*

Current state of the model.

Available options: `created`, `training`, `trained`, `failed`

**tags** `string[]` *required*

Model tags.

**created\_at** `string\<date-time\>` *required*

Timestamp when the model was created.

**updated\_at** `string\<date-time\>` *required*

Timestamp when the model was last updated.

**visibility** `enum\<string\>` *required*

Model visibility setting.

Available options: `public`, `unlist`, `private`

**like\_count** `integer` *required*

Number of likes the model has received.

**mark\_count** `integer` *required*

Number of marks/bookmarks the model has received.

**shared\_count** `integer` *required*

Number of times the model has been shared.

**task\_count** `integer` *required*

Number of tasks associated with the model.

**author** `AuthorEntity · object` *required*

Information about the model author.

**properties**

**\_id** `string` *required*

Author's unique identifier.

**nickname** `string` *required*

Author's nickname.

**avatar** `string` *required*

URL of the author's avatar image.

**train\_mode** `enum\<string\>` (default: full)

Training mode used for the model.

Available options: `fast`, `full`

**samples** `SampleEntity · object[]`

Sample data associated with the model.

**properties**

**title** `string` *required*

Sample title.

**text** `string` *required*

Text content of the sample.

**task\_id** `string` *required*

Task identifier for the sample.

**audio** `string` *required*

URL of the sample audio file.

**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 the model.

**liked** `boolean` (default: false)

Whether the current user has liked the model.

**marked** `boolean` (default: false)

Whether the current user has marked/bookmarked the model.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.