POST
/
model

Since this endpoint requires uploading file, it only accepts multipart/form-data and application/msgpack.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

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
type
enum<string>
required

Model type, tts is for text to speech

Available options:
tts
voices
required

Upload voices files that will be used to tune the model

cover_image
file | null

Model cover image, this is required if the model is public

description
string | null

Model description

enhance_audio_quality
boolean
default:
false

Enhance audio quality

tags

Model tags

texts

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

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

Response

201 - application/json
_id
string
required
author
object
required
cover_image
string
required
created_at
string
required
description
string
required
like_count
integer
required
mark_count
integer
required
shared_count
integer
required
state
enum<string>
required
Available options:
created,
training,
trained,
failed
tags
string[]
required
task_count
integer
required
title
string
required
type
enum<string>
required
Available options:
svc,
tts
updated_at
string
required
visibility
enum<string>
required
Available options:
public,
unlist,
private
languages
string[]
liked
boolean
default:
false
lock_visibility
boolean
default:
false
marked
boolean
default:
false
samples
object[]
train_mode
enum<string>
default:
full
Available options:
fast,
full
unliked
boolean
default:
false