> ## Documentation Index
> Fetch the complete documentation index at: https://docs.miraiminds.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Voices

> Choosing a voice_id for your agent — the two t1 voices, the t3 catalogue, and the one caveat about the language field.

Every agent speaks in one voice, set by `voice.voice_id`. **Which voices exist
depends on the [tier](/general/tiers)**, because the tiers speak through
different engines.

## `t3` — the default

`t3` speaks through a premium third-party catalogue (Sarvam). There is no short
allowlist to memorise: pass the vendor's voice id, e.g. `ashutosh`.

```json theme={null}
{
  "voice": { "voice_id": "ashutosh", "language": "hi-IN" },
  "language": "hi-IN"
}
```

On `t3` **`voice` is required** when you create an agent. There is no safe
default to pick from somebody else's catalogue, so an agent without one is a
`400`.

## `t1` — exactly two voices

`t1` speaks through our own stack, and it loads exactly two voices:

| `voice_id` | Notes                                                                               |
| :--------- | :---------------------------------------------------------------------------------- |
| `ashu`     | Hindi / Hinglish. **The default** — omit `voice` entirely on `t1` and you get this. |
| `aishe`    | Hindi / Hinglish, second option.                                                    |

Anything else is rejected at agent-create time, and the error names both so you
are not left guessing:

```json title="400 Bad Request" theme={null}
{
  "error": {
    "code": "invalid_request",
    "message": "voice.voice_id 'priya' is not available. Use 'ashu' or 'aishe'."
  }
}
```

<Note>
  The same agent can be run at either tier — `tier` is set per call and per
  [campaign](/v2/campaigns), not on the agent. If you create an agent with a `t3`
  voice and then place a `t1` call with it, the voice will not be one `t1` can
  say. Keep one agent per tier when you use both.
</Note>

## Hearing them first

There is no `GET /v2/voices` yet. The live catalogue is the voice picker in the
[console](https://sandbox.voice.miraiminds.co) — open Agent Studio and you can
**hear each voice** before you commit to one. The name in the picker is the
`voice_id`, and the catalogue grows monthly; treat the picker, not this page, as
the source of truth.

<Tip>
  **Listen before you pick.** Voice choice moves answer-through rates more than
  prompt wording does.
</Tip>

## Setting a voice on an agent

```json theme={null}
{
  "name": "Order confirmations",
  "system_prompt": "…",
  "voice": { "voice_id": "ashutosh", "language": "hi-IN" },
  "language": "hi-IN"
}
```

| Field      | Type   | Description                                                                                                                  |
| :--------- | :----- | :--------------------------------------------------------------------------------------------------------------------------- |
| `voice_id` | string | A voice your tier can say. Required on `t3`; optional on `t1`, where it defaults to `ashu`. Unknown on `t1` ⇒ `400`.         |
| `language` | string | Rendering language. Omit to inherit the agent's top-level `language`. **Accepted and stored, not yet honoured** — see below. |

Change it later with `PATCH /v2/agents/{id}`:

```bash theme={null}
curl -X PATCH https://sandbox.voice.miraiminds.co/v2/agents/agt_… \
  -H "Authorization: Bearer sk_live_…" \
  -H "Content-Type: application/json" \
  -d '{ "voice": { "voice_id": "aishe", "language": "hi-IN" } }'
```

See the [Agents reference](/v2/agents#voice) for the full agent shape.

## The language caveat

<Warning>
  **`voice.language` is recorded, not yet applied**

  It is validated, stored, echoed back and carried with the call payload — but
  the voice renders in the agent's **top-level** `language`. Set both to the same
  value and you get what you expect; set them differently and the top-level one
  wins.
</Warning>

Keep `voice.language` and the agent's `language` identical.