> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# Private deployments

## Overview

ElevenAgents runs full conversational agent workflows inside your own cloud account or your own hardware. Text to Speech and Scribe transcription can also be deployed on their own as standalone inference endpoints on Amazon SageMaker or Vertex AI. In both cases, text, audio and transcripts never leave your network.

> **Info**
>
> Private deployments are available on AWS and GCP. We are working closely with Microsoft to release
> an equivalent Azure offering later in H2 2026.

#### Agents in your own network

Run the full ElevenAgents runtime in your VPC, connected to your own LLM, telephony and
retrieval.

#### State-of-the-art models

Access to ElevenLabs' v2 and v2.5 Text to Speech models and Scribe V2 for transcription.

#### Complete data control

All text, audio and call data stays within your infrastructure, meeting strict compliance and
data residency requirements.

#### Enterprise support

Forward-deployed engineers, reference architectures and sizing guidance throughout the rollout.

## Get access

> **Info**
>
> Full private deployment documentation and technical resources are available to authorized
> customers only. For prospective customers, we require an NDA.

To learn more about private deployment options and get access to the technical documentation, contact your ElevenLabs account team or [reach out to our sales team](https://elevenlabs.io/contact-sales).

If you already have access, start with [Getting started](/docs/private-deployment/getting-started).

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.