List Voices | Mesh API Docs

List available TTS voices across every provider, filterable by model brand.

A unified, normalised catalog spanning ElevenLabs, Together, and DeepInfra:

Together voices are fetched live from its /v1/voices endpoint (Cartesia and any other dynamic models).
Kokoro / Orpheus preset voices (shared by Together + DeepInfra) come from a static catalog — DeepInfra exposes no per-model preset listing.
ElevenLabs account voices are fetched live.

Filters (case-insensitive): brand (e.g. elevenlabs, hexgrad, canopylabs, cartesia), model (canonical model_id), and search (substring match on voice id / name). Per-provider fetches are best-effort — a provider that errors is skipped rather than failing the whole listing.

List available TTS voices across every provider, filterable by model `brand`. A unified, normalised catalog spanning ElevenLabs, Together, and DeepInfra: - **Together** voices are fetched live from its `/v1/voices` endpoint (Cartesia and any other dynamic models). - **Kokoro / Orpheus** preset voices (shared by Together + DeepInfra) come from a static catalog — DeepInfra exposes no per-model preset listing. - **ElevenLabs** account voices are fetched live. Filters (case-insensitive): `brand` (e.g. `elevenlabs`, `hexgrad`, `canopylabs`, `cartesia`), `model` (canonical model_id), and `search` (substring match on voice id / name). Per-provider fetches are best-effort — a provider that errors is skipped rather than failing the whole listing.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Query parameters

brandstring or nullOptional

modelstring or nullOptional

searchstring or nullOptional

Response

Successful Response

voiceslist of objects

countintegerDefaults to 0

truncatedbooleanDefaults to false

Errors

422

Unprocessable Entity Error

List available TTS voices across every provider, filterable by model brand.

A unified, normalised catalog spanning ElevenLabs, Together, and DeepInfra:

Together voices are fetched live from its /v1/voices endpoint (Cartesia and any other dynamic models).
Kokoro / Orpheus preset voices (shared by Together + DeepInfra) come from a static catalog — DeepInfra exposes no per-model preset listing.
ElevenLabs account voices are fetched live.

1	{
2	"voices": [
3	{
4	"voice_id": "21m00Tcm4TlvDq8ikWAM",
5	"name": "Rachel",
6	"brand": "elevenlabs",
7	"provider": "elevenlabs",
8	"model": "eleven_monolingual_v1",
9	"language": "en-US",
10	"gender": "female",
11	"preview_url": "https://api.elevenlabs.io/voices/21m00Tcm4TlvDq8ikWAM/preview",
12	"category": "premade"
13	}
14	],
15	"count": 1,
16	"truncated": false
17	}

$	curl https://api.meshapi.ai/v1/audio/voices \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json"