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

# Welcome to Boson AI

> Build real-time voice and multimodal AI agents for natural, responsive conversations.

Boson AI provides infrastructure for real-time voice and avatar experiences. The Higgs API gives developers a family of models for speech generation, audio understanding, lifelike avatars, and interactive agents.

## Higgs models

<CardGroup cols={2}>
  <Card title="Higgs TTS 3" icon="microphone" href="/models/higgs-tts/overview">
    Natural, expressive text-to-speech in 100 languages, with controllable style for real-time voice applications.
  </Card>

  <Card title="Higgs Avatar" icon="face-smile" href="/models/higgs-avatar/overview">
    Avatar video generation from a single still image and a driving voice, built for real-time interaction.
  </Card>

  <Card title="Higgs Realtime" icon="bolt" href="/models/higgs-realtime/overview">
    Speech-to-speech realtime model for voice agents that understand audio and text, call tools, handle interruptions, and stream spoken responses.
  </Card>
</CardGroup>