---
title: Sawtak Arabi documentation
description: Generate Arabic speech for your app or voice agent. Choose a voice, connect to the API, and work with streamed audio.
---

Generate Arabic speech for your voice agent, assistant or application. Choose a voice and send text using the API directly or through the OpenAI SDK.

- [Quickstart](/docs/quickstart) — generate your first audio file.
- [Use with an AI agent](/docs/agent-skill) — generate voiceovers with Claude Code or Codex.
- [Arabic TTS integrations](/docs/integrations) — choose between the API, hosted MCP and coding-agent skill.
- [Hosted MCP](/docs/hosted-mcp) — connect your assistant with OAuth.
- [Authentication](/docs/authentication) — create and configure an API key.

## API endpoints

Base URL: `https://api.sawtakarabi.ai/v1`. Send your [API key](/docs/authentication) with each request. Public voice previews work without a key.

| Endpoint                                                       | Purpose                                                |
| -------------------------------------------------------------- | ------------------------------------------------------ |
| `POST /audio/speech`                                           | [Generate speech](/docs/text-to-speech).               |
| `GET /voices`, `GET /voices/{id}`                              | [Find and inspect voices](/docs/voices).               |
| `GET /voices/{id}/preview`                                     | Play a voice sample.                                   |
| `POST /voices`, `PATCH /voices/{id}`, `DELETE /voices/{id}`    | [Clone and manage voices](/docs/voice-cloning).        |
| `GET /operations/{id}`, `POST /operations/{id}/cancel`         | [Check or cancel a request](/docs/operations).         |
| `GET /me`, `GET /usage`                                        | [Check your balance and usage](/docs/usage).           |
| `GET /history`, `GET /history/{id}`, `GET /history/{id}/audio` | [Retrieve saved recordings](/docs/generation-history). |
| `GET /models`, `GET /models/arabic-tts-1`                      | Discover the `arabic-tts-1` model.                     |

See [Streaming audio](/docs/streaming), [Request limits](/docs/limits), and [Errors](/docs/errors) when building your integration.

Machine-readable documentation: [llms.txt](/llms.txt) and [all guides](/llms-full.txt).