Skip to main content
POST
Create custom voice

Authorizations

Authorization
string
header
required

Your AI Reserve API key (aireserve_api_…) from the API Keys page in the portal (https://portal.aireserve.com/keys).

Body

multipart/form-data
name
string
required

Display name for this custom voice.

Maximum string length: 255
language
string
required

BCP-47 language code (e.g. en, en-US).

file
file
required

Reference audio file. Recommended: single-speaker mono WAV at 24 kHz, 90–120 s, quiet environment. Max 31 MB / 120 s.

Must be "true". Attests that the speaker has given informed consent to having their voice cloned.

Available options:
true
description
string

Optional free-text description.

Maximum string length: 10000
gender
enum<string>

Speaker gender.

Available options:
male,
female,
neutral
accent
string

Speaker accent (free text).

Maximum string length: 100
age
enum<string>

Approximate speaker age bracket.

Available options:
young,
middle-aged,
old
use_case
enum<string>

Intended use-case hint for voice model tuning.

Available options:
conversational,
narration,
characters,
educational,
advertisement,
social_media,
entertainment
tone
enum<string>

Tonal quality hint.

Available options:
warm,
casual,
professional,
friendly,
authoritative,
expressive,
calm

Response

Custom voice created.

Allowlisted projection of an xAI custom voice object returned by create, read, and update operations. xAI-internal fields (team IDs, consent state) are excluded.

voice_id
string
required
Pattern: ^[a-z0-9]{8}$
name
string | null
description
string | null
gender
string | null
accent
string | null
age
string | null
language
string | null
use_case
string | null
tone
string | null
created_at
string<date-time>