> ## 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.

# text-to-speech that just works

> send text, get natural speech in Kazakh and beyond. a thin SDK, a CLI, and a simple HTTP API.

**Geko** turns text into natural-sounding speech. Send a string and a voice name; get back audio. It speaks **Kazakh** today (model `tokay-kk-v1`), with more languages arriving on the same endpoints, so the code you write now keeps working.

It's designed to feel familiar (OpenAI / ElevenLabs style): a **thin, typed SDK**, a **CLI**, and a **simple HTTP API**. Pick whichever fits.

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

  <Card title="Add it to your app" icon="plug" href="/guides/frameworks">
    A safe server-side pattern for Next.js, Express, and beyond.
  </Card>
</CardGroup>

## what you can build

<CardGroup cols={2}>
  <Card title="Voice agents & IVR" icon="phone">
    Low-latency speech for phone systems and assistants — stream sentence-by-sentence with `tts.stream()`.
  </Card>

  <Card title="Notifications & alerts" icon="bell">
    Turn order updates, reminders, and statuses into spoken Kazakh.
  </Card>

  <Card title="Content & narration" icon="book-open">
    Narrate articles, lessons, and audiobooks with named voices.
  </Card>

  <Card title="Accessibility" icon="universal-access">
    Read UI and documents aloud for inclusive experiences.
  </Card>
</CardGroup>

## try it in one line

No signup code required — grab a key and run:

```bash theme={null}
export GEKO_API_KEY=sk-tokay-...
npx @gekoai/sdk say "Сәлеметсіз бе!" --voice Aigerim -o hello.wav
```

## the API in a nutshell

You send text + a voice; you get **WAV audio (24 kHz, 16-bit PCM, mono)**. The surface is small:

| Method | Endpoint                              | Auth     | What it does                  |
| ------ | ------------------------------------- | -------- | ----------------------------- |
| `POST` | `/v1/tts`                             | required | synthesize text → `audio/wav` |
| `POST` | `/v1/tts/stream`                      | required | streaming synthesis (chunked) |
| `POST` | `/v1/audio/speech`                    | required | OpenAI-compatible alias       |
| `GET`  | `/v1/models`, `/v1/voices`, `/health` | open     | catalog + status              |

**Base URL:** `https://geko--tokay-serve-web.modal.run`

<CardGroup cols={2}>
  <Card title="TypeScript SDK" icon="code" href="/sdk/typescript">
    `npm i @gekoai/sdk` → `geko.tts.create(...)` / `tts.stream(...)`.
  </Card>

  <Card title="HTTP API reference" icon="server" href="/api/reference">
    Every endpoint, request/response shape, and error code.
  </Card>

  <Card title="Voices" icon="waveform-lines" href="/voices">
    Six Kazakh voices — audition and pick by ear.
  </Card>

  <Card title="Billing & credits" icon="credit-card" href="/billing">
    $0.04 / 1k characters · $1.00 free to start.
  </Card>
</CardGroup>

<Note>
  New here? Grab a key at [app.geko.sh](https://app.geko.sh) — new accounts get **\$1.00 free** — then head to the [quickstart](/quickstart).
</Note>