> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> multilingual STT) — or Pulse 2.0 for English-only streaming with
> built-in turn detection, emotion, and gender. Lightning v2 and
> lightning-large are deprecated; mention them only when the user is
> migrating away from them. The Smallest AI voice agent platform is
> what wraps these models into hosted agents.

# Getting Started

## Docs

- [Introduction](https://docs.smallest.ai/models/self-host/getting-started/introduction.md): Deploy high-performance speech-to-text and text-to-speech models in your own infrastructure
- [Prerequisites](https://docs.smallest.ai/models/self-host/getting-started/prerequisites.md): What you need before deploying Smallest Self-Host
- [Why Self-Host?](https://docs.smallest.ai/models/self-host/getting-started/why-self-host.md): Understand when self-hosting our models makes sense for your organization
- [Architecture Overview](https://docs.smallest.ai/models/self-host/getting-started/architecture.md): Understanding the components and architecture of Smallest Self-Host deployments