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

# Text-to-Speech Overview

> Synthesize natural speech from text via WebSocket streaming, REST API, or in-call playback.

## 1. Choose your interface

<CardGroup cols={3}>
  <Card title="WebSocket Streaming" icon="bolt" href="/docs/voice/tts/websocket-streaming">
    Real-time streaming. Send text, receive audio chunks as they're synthesized.
  </Card>

  <Card title="REST API" icon="server" href="/docs/voice/tts/rest-api">
    HTTP POST. Get audio back as binary, base64, or async URL. OpenAI SDK compatible.
  </Card>

  <Card title="In-Call Playback" icon="phone" href="/docs/voice/tts/in-call-playback">
    TTS during live calls via Call Control `speak` or TeXML `<Say>`.
  </Card>
</CardGroup>

## 2. Choose a pre-built voice

<CardGroup cols={2}>
  <Card title="Telnyx" icon="microchip" href="/docs/voice/tts/providers/telnyx">
    Natural, NaturalHD, Ultra, Kokoro, Qwen3TTS, xAI Grok.
  </Card>

  <Card title="Third-Party Providers" icon="puzzle-piece" href="/docs/voice/tts/providers/aws">
    AWS Polly, Azure, ElevenLabs, Minimax, MurfAI, Rime, Resemble, Inworld.
  </Card>
</CardGroup>

## 3. Or create your own

<CardGroup cols={1}>
  <Card title="Voice Design Lab" icon="wand-magic-sparkles" href="/docs/tts-stt/voice-cloning">
    Clone and design custom voices. Available on select providers: Qwen3TTS, Minimax, ElevenLabs, Resemble.
  </Card>
</CardGroup>