> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). 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.

# Introduction

> Deploy high-performance speech-to-text and text-to-speech models in your own infrastructure

Smallest Self-Host enables you to get the same powerful TTS and STT capabilities as our cloud service while keeping your data under complete control.

## Deployment Options

#### [Docker STT](/models/self-host/docker-setup/stt-deployment/quick-start)

Deploy speech-to-text with Docker. Best for development, testing, and small-scale production.

#### [Docker TTS](/models/self-host/docker-setup/tts-deployment/quick-start)

Deploy text-to-speech with Docker. Quick setup for voice synthesis workloads.

#### [Kubernetes STT](/models/self-host/kubernetes-setup/quick-start)

Production-grade STT with autoscaling and high availability on Kubernetes.

Kubernetes deployment is currently available for **STT only**. TTS Kubernetes support is coming soon.

## Resources

#### [Architecture](/models/self-host/getting-started/architecture)

System components and data flow

#### [Why Self-Host?](/models/self-host/getting-started/why-self-host)

Benefits of self-hosting

#### [Prerequisites](/models/self-host/getting-started/prerequisites)

Requirements and credentials

## Support

* **Email**: [support@smallest.ai](mailto:support@smallest.ai)
* **Discord**: [Join our community](https://discord.gg/9WtSXv26WE)