The Voice object

Fields returned for a voice.

A voice is returned by List voices and Get a voice. The developer-relevant fields are below. Timestamps are Unix epoch milliseconds.

id · string

Unique voice id (24-character hex). Use it with the synthesize endpoints.

name · string

Display name.

description · string

Optional long-form description.

status · string

Whether the voice is usable. Only ready voices can synthesize. A voice still being created reports processing (and failed if creation didn’t succeed). See Working with voices.

clone_method · string

How the voice was created: instant, professional, design, or remix.

visibility · string

private, org, or public.

primary_language · string

Default language (BCP-47, e.g. en). Used when a synthesis request omits language.

labels · object[]

Searchable key/value tags, e.g. { "key": "accent", "value": "american" }. Common keys: accent, gender, age, use_case.

settings · object

Optional synthesis defaults for the voice (stability, similarity, style, speed, pitch, volume, use_speaker_boost, emotion, engine_params). Present only when configured.

sample_audio_url · string

Public URL of a short preview clip, when available.

base_voice_id · string

Present when the voice was saved/derived from another voice (clone_method: remix).

created_at · integer

Creation time (Unix epoch milliseconds).

updated_at · integer

Last update time (Unix epoch milliseconds).

Example

{
  "id": "665f1a2b3c4d5e6f7a8b9c0d",
  "name": "Studio Narrator",
  "description": "Warm, neutral narration voice.",
  "status": "ready",
  "clone_method": "instant",
  "visibility": "public",
  "primary_language": "en",
  "labels": [
    { "key": "accent", "value": "american" },
    { "key": "gender", "value": "female" }
  ],
  "sample_audio_url": "https://storage.googleapis.com/.../sample.wav",
  "created_at": 1717939200000,
  "updated_at": 1717939260000
}