Use cases

AI avatars for places where data has to stay put

Bank branches and ATMs, hospitals and clinics, show floors and museums, and the devices you build: each needs a face and a voice that runs close to the people using it. bitHuman renders on local hardware, on your own servers, or fully offline, so you decide what reaches us.

Talk to us

By setting

Banking & ATMs An avatar that runs inside the terminal, so customer conversations can stay on your network.
Healthcare Patient-facing avatars on hardware you control; patient audio and transcripts need never reach us.
Trade shows, museums & kiosks Runs on the local machine, and with an offline license needs no venue internet.
Embedded devices SDKs for Android, iOS, macOS and Linux that render on the device's own processor.

Where the avatar renders, and what reaches bitHuman

bitHuman cloud

The avatar renders: On bitHuman's servers, in the US
What reaches bitHuman: The session's audio and conversation, to run it. Transcripts are kept with your agent; deleting the agent deletes them.
Best for: The fastest start: web pages, apps and APIs

Your servers

The avatar renders: On your own Mac or Linux machines, on-premises or in your cloud account; a standard Linux PC needs no GPU
What reaches bitHuman: A credential check when a session starts, the avatar download, and usage reports with no audio, video or conversation text
Best for: On-premises, data-center and private-cloud deployments

On the device

The avatar renders: On the iPhone, iPad, Mac or Android device in front of the user, or in a WebGPU browser tab
What reaches bitHuman: With your own voice and language services, usage metering only — never audio, video or conversation text
Best for: Apps, kiosks and embedded screens

Fully offline

The avatar renders: On your Linux PCs and terminals
What reaches bitHuman: Nothing while it runs: usage is metered on the machine, and no reconnection is required
Best for: Kiosks, ATM machines, trade shows and embedded screens — Business and Enterprise