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

# Choosing a Voice

> Pick a built-in voice, clone your own, and set its defaults.

Every synthesis request names a voice by UUID. The voice determines which model runs, so it
is the first thing to settle.

## Built-in voices

Three voices are available to every organization and are a reasonable default for most
applications:

| Voice   | UUID                                   | Character                                                                                               |
| ------- | -------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| Karen   | `29158307-9893-4149-8a75-bc9ce313d64e` | Mature female, General American, nasal and deadpan, moderate pace. Suits support lines and IVR prompts. |
| Matthew | `1d4dc605-071b-4eee-81b3-099b2894d0d1` | Mature male, General American.                                                                          |
| River   | `2f29fdbb-c55e-4add-9c7c-93437ebf379d` | Light and playful, moderate pace. Suits podcasts and advertisements.                                    |

## Listing everything available to you

[List Voices](/api-v1/get/voices) returns the built-ins, anything you have cloned, and
anything added from the public library:

```bash theme={null}
curl "https://api.bland.ai/v1/voices" -H "Authorization: Bearer $BLAND_API_KEY"
```

The native [`/v2/tts`](/api-v2/post/tts) and [`/v2/tts/ws`](/api-v2/post/tts-ws) surfaces
require a UUID. Two voices can share a display name, so resolving one would mean guessing
which you meant. The [OpenAI-compatible endpoint](/api-v2/post/audio-speech) also accepts its
documented OpenAI voice aliases.

## Prefer a BTTS\_V3 voice

`BTTS_V3` is the current generation: highest fidelity, and the `expressiveness` and
`stability` controls are calibrated for it. It renders natively at 48 kHz, so requesting
48 kHz avoids a resample.

`BTTS_V2` voices still synthesize. The controls are not tuned for them and will have less
predictable effects. The `x-model` response header tells you which model a voice resolved to.

## Cloning a voice

A clone needs one clean sample of about ten seconds. Quality of the sample sets the ceiling
on quality of the voice, so it is worth trimming properly:

* One speaker, clearly enunciated
* No background noise, music, or reverb
* At least 100 ms of silence at each end, so nothing is clipped mid-word
* Emotional variety in the delivery, which yields a more expressive clone

Both engines are single-sample by design and cover 17+ languages. `BTTS_V3` is the default
and what you want unless you have a specific reason to pin the previous generation.

Clone from the dashboard at
[Voices → Studio](https://app.bland.ai/dashboard/voices?tab=studio), or programmatically with
[Clone Voice](/api-v1/post/clone). A cloned voice is private to your organization and usable
immediately.

<Tip>
  If a clone sounds broken when it code-switches or speaks a language absent from the sample,
  the sample is the problem, not the settings. Clone again from a recording that contains the
  languages you need.
</Tip>

## Per-voice defaults

Each voice carries its own default delivery settings, editable in Studio or through
[Update Voice Config](/api-v1/patch/voices-id-config). Anything you send in a request's
`controls` object overrides them for that request only.

Set the defaults on the voice when every use should sound the same. Override per request when
one flow needs a different read, such as a warm greeting and a flat account-balance readout from the
same voice, for example. See [Writing for speech](/tts/writing-for-speech) for what the
controls do.

## The voice is fixed for a WebSocket session

On [`WSS /v2/tts/ws`](/api-v2/post/tts-ws), the voice is set by `init` and holds for the life
of the connection. That is what lets one warm synthesis session serve every turn. To change
voices, open another connection.

## Public library voices

[Shared voices](/api-v1/get/voices-shared) are published by other creators. Add one to your
library with [Add Library Voice](/api-v1/post/voices-library-add-id) before using it.

Some carry a per-character creator fee on top of the standard rate. The exact charge for a
request comes back in the `x-cost` header.

***

Docs for agents: [llms.txt](/llms.txt)