List and manage voices | EmpirioLabs AI Docs

Returns the voice catalog for a TTS model. Models that serve this endpoint today are Inworld TTS Mini / Max / 2 and Qwen Audio 3.0 TTS. Use the returned voice id on /v1/audio/speech or /v1/audio/speech:stream.

model is required. Voice catalogs are per-model and differ in both contents and response shape, so the request must say which TTS model to list. Omitting it returns 400 missing_required_parameter.

The response is shaped by the model that serves it, since each provider describes its voices differently. Qwen Audio 3.0 TTS returns id, name, gender, age, trait, scenario, language, kind (base or system), and tiers (which of plus / flash can use the voice), plus a total count and the resolved model. Read the model’s own documentation page for its exact fields.

Returns the voice catalog for a TTS model. Models that serve this endpoint today are Inworld TTS Mini / Max / 2 and Qwen Audio 3.0 TTS. Use the returned voice id on `/v1/audio/speech` or `/v1/audio/speech:stream`. `model` is required. Voice catalogs are per-model and differ in both contents and response shape, so the request must say which TTS model to list. Omitting it returns 400 `missing_required_parameter`. The response is shaped by the model that serves it, since each provider describes its voices differently. Qwen Audio 3.0 TTS returns `id`, `name`, `gender`, `age`, `trait`, `scenario`, `language`, `kind` (`base` or `system`), and `tiers` (which of `plus` / `flash` can use the voice), plus a `total` count and the resolved `model`. Read the model's own documentation page for its exact fields.

Authentication

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Query parameters

modelstringRequired

TTS model whose voice catalog to return, for example qwen-audio-3-0-tts or inworld-tts-max.

languagestringOptional

Filter by language, matched case-insensitively as a substring, for example english. Supported by Qwen Audio 3.0 TTS.

genderstringOptional

Filter by voice gender, for example female. Supported by Qwen Audio 3.0 TTS.

tierstringOptional

Filter to voices usable by one tier of a tiered model, for example flash. Supported by Qwen Audio 3.0 TTS.

qstringOptional

Free-text search across voice id, name, trait, and use case. Supported by Qwen Audio 3.0 TTS.

Response

Voice catalog. Field names vary by model; the example below is Qwen Audio 3.0 TTS.

objectstringOptional

modelstringOptional

totalintegerOptional

datalist of objectsOptional

Errors

400

Bad Request Error

1	{
2	"object": "list",
3	"model": "qwen-audio-3-0-tts",
4	"total": 1032,
5	"data": [
6	{
7	"id": "loongolivialin",
8	"name": "Olivia Lin",
9	"gender": "Female",
10	"age": 28,
11	"trait": "Tender and Intellectual",
12	"scenario": "Emotional Companionship",
13	"language": "English",
14	"kind": "base",
15	"tiers": [
16	"plus",
17	"flash"
18	]
19	}
20	]
21	}