GET
/
voices

Query Parameters

mode
enum<string>
default: tts-basic

The type of voice to list.

tts-basic: Basic text-to-speech voices.

tts-reference: Voices which can be conditioned on pitch and duration.

tts-all: All voices which can produce audio from text input.

tts-rap: Voices that can be used to create raps.

v2v: Voices which can be used for voice conversion. These accept an audio input.

Available options:
tts-basic,
tts-reference,
tts-all,
v2v,
all,
tts-rap
language
enum<string>
Available options:
english,
dutch,
spanish,
portuguese,
polish
is_private
boolean
owner
boolean
name
string

Response

200 - application/json
added_at
string
architecture
string
category
string
contributors
string[]
controls
boolean
display_name
string
required
is_active
boolean
memberships
object[]
is_private
boolean
required
is_primary
boolean
name
string
required
voice_actor
string
tags
string[]
images
string[]
samples
object[]
symbol_set
string
voicemodel_uuid
string
hifi_gan_vocoder
string
ml_model_id
integer
speaker_id
integer
language
string
gender
string
mood
string
style
string
accent
string
age
string
description
string
image_url
string
features
string[]