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

# Voice overview

> Generate speech, transcribe audio, and build realtime voice agents with Inworld Voice.

Inworld Voice brings together text-to-speech, speech-to-text and the Realtime API. Choose the API for the audio task you want to build.

<CardGroup cols={3}>
  <Card title="Text-to-Speech (TTS)" icon="waveform-lines" href="https://docs.inworld.ai/tts/tts.md">
    Turn text into natural speech for your app, agent or character.
  </Card>

  <Card title="Speech-to-Text (STT)" icon="microphone" href="https://docs.inworld.ai/stt/overview.md">
    Transcribe recordings or live audio.
  </Card>

  <Card title="Realtime API" icon="comment-dots" href="https://docs.inworld.ai/realtime/overview.md">
    Build a voice agent that listens and talks in real time.
  </Card>
</CardGroup>

## Make your first request

- [TTS quickstart](https://docs.inworld.ai/quickstart-tts.md): generate speech from text.
- [STT quickstart](https://docs.inworld.ai/stt/quickstart.md): transcribe audio.
- [Realtime quickstart](https://docs.inworld.ai/realtime/quickstart-websocket.md): start a live voice conversation.

## Connect voice and inference

Use [Inworld Inference](https://docs.inworld.ai/router/introduction.md) for text, image, video and decision models. To generate a text answer and speak it in one API call, see [Voice responses (LLM + TTS)](https://docs.inworld.ai/router/guides/llm-plus-tts.md).

For credentials, limits and usage, see [Go to production](https://docs.inworld.ai/resources/production.md).