# Models & voices: List voices (https://docs.envocal.ai/api-reference/models-and-voices/list-voices/) > The voices the tenant's agents can speak with, in display order. An agent's voice is one of these keys, and it must work with the agent's model: pass model to get exactly the voices an agent on that model can use. Each voice has a short sample clip (sampleUrl). ## GET `/v1/tenants/{tenantId}/voices` The voices the tenant's agents can speak with, in display order. An agent's `voice` is one of these keys, and it must work with the agent's model: pass `model` to get exactly the voices an agent on that model can use. Each voice has a short sample clip (`sampleUrl`). **Required permission:** `agents:read` ### Parameters | Name | In | | Type | Description | | --- | --- | --- | --- | --- | | `tenantId` | path | required | string | Tenant id, or `current` for the key's own tenant. Must be the key's tenant or one of its sub-tenants. | | `model` | query | | string | Only voices an agent on this model can use, e.g. `gpt-realtime-1.5`. | | `provider` | query | | string | Only voices from this provider, e.g. `openai`. | | `gender` | query | | string | Only voices of this gender: `female`, `male` or `neutral`. | | `age` | query | | string | Only voices of this age: `young`, `middle-aged` or `old`. | | `language` | query | | string | Only voices that speak this language (BCP 47, e.g. `sv` or `en-GB`): with `model`, on that model; without, on any of their models. Voices whose primary language it is come first. | ### Responses **200** — VoiceDto[]: The voices. | Field | Type | | Description | | --- | --- | --- | --- | | `key` | string | required | The value to put in an agent's `voice`, e.g. `marin`. | | `name` | string | required | Display name. | | `description` | string | nullable | How the voice sounds or what it suits. | | `provider` | AiProviderDto | required | The company behind the voice. | | `gender` | `female` \| `male` \| `neutral` | required | How the voice sounds. | | `age` | `young` \| `middle-aged` \| `old` | nullable | How old the voice sounds; null when not stated. | | `language` | string | nullable | The voice's primary language as a BCP 47 code without region (e.g. `en`); null when it has no primary language. | | `region` | string | nullable | Region of the primary language (e.g. `GB`), if any. | | `accent` | string | nullable | Accent or dialect of the primary language in words (e.g. `London`), if any. | | `multilingual` | boolean | | Whether the voice also speaks languages besides its primary language. Which ones, on a given model: those in the voice's `languages` that the model also speaks, or, when the voice's `languages` is empty, all the model's `languages`. When neither lists any, the voice isn't limited to a set of languages. | | `languages` | string[] | required | For a multilingual voice that speaks fewer languages than its model: the languages besides its primary language (BCP 47). Empty when it speaks all its model's languages. | | `tags` | string[] | required | Describing words, e.g. `warm`, `calm`. | | `sampleUrl` | string | nullable | URL of a short sample clip (an audio file browsers can play, e.g. FLAC or MP3). | | `models` | string[] | required | Keys of the models that can speak with this voice. | | `status` | `preview` \| `active` \| `deprecated` | required | `preview`, `active` or `deprecated`. | **400**: Unknown model. **401**: Missing, invalid, revoked or expired API key. **403**: The key lacks the required permission, or the tenant/resource is outside its reach. **429**: Rate limit exceeded. Retry after the number of seconds in the Retry-After header. ### Example ```bash curl -X GET "https://api.envocal.ai/v1/tenants/current/voices" \ -H "Authorization: Bearer evk_eu_..." ```