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

# Voices

> The six Kazakh voices of tokay-kk-v1 — and how to audition them.

Model `tokay-kk-v1` (Kazakh) ships with **six** named voices — three female, three male. Pass one by `name`; omit `voice` and you get the default, **Aigerim**.

```ts theme={null}
await geko.tts.create({ text: "Сәлем", voice: "Aigerim" });
```

## The catalog

<CardGroup cols={2}>
  <Card title="Aigerim" icon="waveform-lines">
    **female · warm, professional** — the default. Reception and customer support.
  </Card>

  <Card title="Arman" icon="waveform-lines">
    **male · confident, professional** — support, IVR, announcements.
  </Card>

  <Card title="Ainur" icon="waveform-lines">
    **female · bright, energetic** — promos and upbeat greetings.
  </Card>

  <Card title="Aruzhan" icon="waveform-lines">
    **female · youthful, clear** — support and notifications.
  </Card>

  <Card title="Sanzhar" icon="waveform-lines">
    **male · neutral, precise** — information, readouts, IVR.
  </Card>

  <Card title="Yerlan" icon="waveform-lines">
    **male · calm, warm** — explanations and long-form.
  </Card>
</CardGroup>

## Always fetch the live list

<Note>
  The catalog grows and changes — **don't hard-code it.** Pull it at runtime (no API key needed).
</Note>

<CodeGroup>
  ```ts SDK theme={null}
  const { voices } = await geko.tts.voices("tokay-kk-v1");
  // [{ name, gender, style, best_for }, ...]
  ```

  ```bash CLI theme={null}
  gekoai voices --json
  ```

  ```bash curl theme={null}
  curl "https://geko--tokay-serve-web.modal.run/v1/voices?model=tokay-kk-v1"
  ```
</CodeGroup>

Each entry has `name`, `gender`, `style`, and `best_for` — enough to build a voice picker or route by use case. See [`GET /v1/voices`](/api-reference/catalog/list-voices).

## Auditioning

Generate a one-line sample per voice to pick by ear:

```bash theme={null}
for v in Aigerim Arman Ainur Aruzhan Sanzhar Yerlan; do
  gekoai say "Сәлеметсіз бе! Менің атым $v." --voice "$v" -o "sample_$v.wav"
done
```

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    From an API key to your first `hello.wav`.
  </Card>

  <Card title="Streaming audio" icon="waveform-lines" href="/guides/streaming">
    Play a long reply sentence-by-sentence.
  </Card>

  <Card title="Latency & quality" icon="gauge-high" href="/guides/latency">
    Tune `nfe` for speed or fidelity.
  </Card>

  <Card title="API reference" icon="server" href="/api/reference">
    Every endpoint, with a live playground.
  </Card>
</CardGroup>