Skip to main content
POST
cURL

Continue building

Designing a voice

Generate, audition, and save previews.

Design a voice

Write a voice description and preview script.

Convert text to speech

Generate audio without word timing.

Authorizations

xi-api-key
string
header
required

Breeze Developer API key.

Path Parameters

generated_voice_id
string
required

Preview ID returned by a voice preview creation endpoint. See Saving a preview.

Body

application/json
gender
enum<string> | null

Stable gender code, or null when not classified. See Metadata options.

Available options:
male,
female,
neutral
age
enum<string> | null

Stable age code, or null when not classified. See Metadata options.

Available options:
child,
young,
middle_aged,
old
tone
enum<string>[]

Zero to three distinct stable tone codes. See Metadata options.

Maximum array length: 3
Available options:
warm,
calm,
bright,
gentle,
energetic,
authoritative,
sincere,
weary,
precise,
refined,
urgent,
friendly,
articulate,
steady,
playful,
compassionate,
reflective,
measured,
rhythmic,
passionate
accent
enum<string> | null

Stable accent code, or null. Valid only for en or zh and must match language_code. See Metadata options, accent codes.

Available options:
american,
british,
scottish,
irish,
australian,
canadian,
us_southern,
us_new_york,
indian,
south_african,
russian,
japanese,
korean,
chinese,
mandarin_northeastern,
mandarin_shaanxi,
mandarin_shanghai,
mandarin_sichuan,
mandarin_henan,
mandarin_beijing,
mandarin_taiwan,
cantonese
voice_name
string | null

Display name, up to 80 characters. Clone previews default to their preview name; Remix previews default to the source voice name. Required for other preview types.

Maximum string length: 80
voice_description
string | null

Optional description stored with the saved voice. Remix previews default to the source description; an empty string clears it.

Maximum string length: 1000
language_code
enum<string> | null

Required saved audio language. Use a supported language code. See supported language codes.

Available options:
af,
ar,
bg,
bn,
bs,
ca,
cs,
da,
de,
el,
en,
es,
et,
eu,
fa,
fi,
fr,
gl,
he,
hi,
hu,
id,
is,
it,
ja,
kn,
ko,
lt,
mr,
ms,
ne,
nl,
no,
pl,
pt,
ro,
ru,
sk,
sl,
sq,
sv,
sw,
ta,
te,
th,
tl,
tr,
uk,
ur,
vi,
zh
tags
string[]

Tags stored with the saved voice. Spelling is preserved; matching and deduplication ignore case. See Tags and favorites.

Maximum array length: 20
Maximum string length: 128

Response

Saved voice.

voice_id
string
required
name
string
required
origin
string
required
language_code
enum<string>
required
Available options:
af,
ar,
bg,
bn,
bs,
ca,
cs,
da,
de,
el,
en,
es,
et,
eu,
fa,
fi,
fr,
gl,
he,
hi,
hu,
id,
is,
it,
ja,
kn,
ko,
lt,
mr,
ms,
ne,
nl,
no,
pl,
pt,
ro,
ru,
sk,
sl,
sq,
sv,
sw,
ta,
te,
th,
tl,
tr,
uk,
ur,
vi,
zh
gender
enum<string> | null
required
Available options:
male,
female,
neutral
age
enum<string> | null
required
Available options:
child,
young,
middle_aged,
old
tone
enum<string>[]
required
Maximum array length: 3
Available options:
warm,
calm,
bright,
gentle,
energetic,
authoritative,
sincere,
weary,
precise,
refined,
urgent,
friendly,
articulate,
steady,
playful,
compassionate,
reflective,
measured,
rhythmic,
passionate
accent
enum<string> | null
required
Available options:
american,
british,
scottish,
irish,
australian,
canadian,
us_southern,
us_new_york,
indian,
south_african,
russian,
japanese,
korean,
chinese,
mandarin_northeastern,
mandarin_shaanxi,
mandarin_shanghai,
mandarin_sichuan,
mandarin_henan,
mandarin_beijing,
mandarin_taiwan,
cantonese,
mandarin_guangdong,
mandarin_yunnan
tags
string[]
Maximum array length: 20
Maximum string length: 128
is_favorited
boolean
default:false
preview_url
string | null
description
string | null
created_at_unix
integer | null