Deployment options

Where the avatar renders: pick the mode that fits your users and data.

Every mode uses the same avatar and the same API secret. What changes is where the avatar renders, where the conversation runs, and what reaches bitHuman.

Choosing a mode

You want to	Start here
Build for the web, with the fewest moving parts	bitHuman cloud, starting with the web embed
Keep audio and video on your network	Your servers or on the device, with the local conversation brain or your own models; what reaches bitHuman: Data flows & privacy
Pay the lowest per-minute rate	Render on the device or on your servers (rates)
Run with no reliable internet at the site	Fully offline, on the Business and Enterprise plans
Plan for a branch, a clinic or a show floor	Use cases

Compare

bitHuman cloudCreator plan or higher
The avatar renders
on bitHuman's servers, in the US
The conversation runs
on bitHuman's voice service, or with your own provider keys
What reaches bitHuman
the session's audio and conversation, to run it
Network
required for the whole session
Price
4 credits per minute (Essence 2, Expression 2)
Products
web embed, REST API, LiveKit plugin, cloud avatar in your room
Models
Essence 2, Expression 2, Essence 1, Expression 1
Your serversCreator plan or higher
The avatar renders
on your own Mac or Linux machines
The conversation runs
your choice: the CLI's local conversation brain, your own services, or bitHuman's
What reaches bitHuman
a credential check, the avatar download, and usage reports with no audio, video or text
Network
to start; rendering continues through a drop of up to 5 minutes
Price
2 credits per minute (Essence 2, Expression 2)
Products
CLI, Python SDK, LiveKit plugin (model_path)
Models
Essence 2, Expression 2, Essence 1
On the deviceCreator plan or higher
The avatar renders
on the iPhone, iPad, Mac or Android phone in front of the user, or in a WebGPU browser tab
The conversation runs
your app's choice; with the web embed, on bitHuman's servers
What reaches bitHuman
with your own voice and language services, usage metering only, never audio, video or conversation text
Network
to start; rendering continues through a drop of up to 5 minutes
Price
2 credits per minute (Essence 2, Expression 2)
Products
Swift package, Android SDK, Flutter plugin, web embed with render=local
Models
Essence 2, Expression 2
Fully offlineBusiness & Enterprise
The avatar renders
on your Linux and macOS computers
The conversation runs
agreed with sales for your site
What reaches bitHuman
usage is metered on the machine; no reconnection is required
Network
off the internet; creating the avatar happens online first
Price
from 100,000 credits; bought in the console or through sales
Products
Linux PCs and terminals, Macs with Apple silicon (Python)
Models
Essence 1 (Linux x86_64 and ARM64, macOS on Apple silicon); Essence 2 and Expression 2 (Linux x86_64)

Both models run live on a standard Linux PC with no GPU: CPU only (no GPU). Every mode bills active session time, talking or idle, to the second (pricing).

Fully offline

Offline license is only available to Business and Enterprise clients who want to run realtime avatars completely locally, off the internet — e.g. kiosks, trade shows, ATM machines, embedded screens. Linux and macOS computers (Apple silicon); bought in the console or through sales. Fully offline

The overview to share with your team is on bithuman.ai: where AI avatars run.