Fully offline

What it is

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 x86_64: Expression 2 now; Essence 1 and Essence 2 come later. Arranged through sales.

• Plans: Business & Enterprise.
• Price: one license per character: 1 character $899 · 5 for $2,990 · 25 for $9,900 (Business) · 100 for $24,900 (Enterprise). Unlimited: by quote. See the pricing page.
• While your plan is active: your licenses work while your Business or Enterprise plan is active. If the plan ends, they keep working for 30 days, then the characters stop loading until a plan is active again.
• Connectivity: offline devices connect before the license file runs out: about once a year on an annual plan, at least every 30 days on a monthly plan.

Contact sales to arrange an offline license.

Compare every mode: Deployment options.

Where it renders

Creating the avatar from a portrait happens in the bitHuman cloud; the finished avatar model then runs on your machines.

Speed

An offline machine is a Linux PC or a Mac with Apple silicon. How fast each model renders on a Linux PC with no GPU is on CPU only (no GPU).

Price

Limits

Runs fully offline on Linux x86_64: Expression 2 now; Essence 1 and Essence 2 come later.

Use the Python package 2.12.8 or later: it reports a refused credential as an error instead of a black first frame. On Linux, the Python package and the bitHuman CLI (2.8.4 or later) both run offline packs; on a Mac, the Python package. Expression 1 has no offline pack.

• Phones and browsers stay online: the Swift package, the Android SDK and the web embed check your credential when a session starts.
• Creation is online: you create the avatar from a portrait in the bitHuman cloud before it runs offline.
• One model per process: run each model in its own process.
• File rendering: without a pack, bithuman render and Python’s render() sign in online and bill your account. With an installed pack that covers the avatar, they run fully offline, with no API secret, and spend the pack.

First command

1. Arrange your offline license through sales: one license per character, for Expression 2 on Linux x86_64. Sales confirms the steps for your machines.

2. Redeem it once, on the machine that will run it, while it is online, with your account’s API secret and bitHuman 2.12.8 or later:

   pip install -U "bithuman>=2.12.8"
   export BITHUMAN_API_SECRET=...
   python -m bithuman pack redeem

   For Expression 2, install "bithuman[expression-2]>=2.12.8" instead. With the bitHuman CLI on Linux (2.8.4 or later), bithuman pack redeem with BITHUMAN_API_SECRET set does the same.

   This binds the pack to this machine and installs it; on a Mac it is sealed with the Mac’s Secure Enclave. If the install step fails, python -m bithuman pack redeem --file <pack> retries it from the copy kept in ~/.bithuman/packs/, with no connection and no second charge.

3. Prepare the machine once while online. Render your avatar once before you disconnect (python -m bithuman render <avatar> <audio>), or with the CLI run bithuman pull <avatar>. This downloads the avatar and the engine files its model needs; a render is metered by the pack like any other.

4. Run offline. The machine now runs fully offline, with no API secret, until the pack’s credits are spent. Credits are metered on the machine, at the self-hosted rate for active session time. Billing: How billing works. It never has to reconnect.

The overview to share with your team is on bithuman.ai: offline AI avatars for kiosks and terminals.