Frequently asked questions
Pricing
What does a minute cost?
On your own hardware, Essence 2 and Expression 2 use 2 credits a minute; in our cloud, 4. At $1 per 100 credits that's about $0.02 and $0.04, billed to the second, talking or idle.
What changes on 12 October?
From 2026-10-12, API and SDK use requires the Creator plan or higher, and Free accounts cannot create agents or buy top-ups. A Free account with top-up credits bought before 2026-09-27 keeps API and SDK access until those credits are spent.
Can I pay yearly?
Yes. Annual plans bill twelve months of credits up front.
Can I cancel?
Cancel any time in the console; your plan runs to the end of the period. Upgrades apply at once, prorated.
Do credits roll over?
Top-up credits never expire and are spent after plan credits. Plan credits come with each billing period.
Deployment & privacy
Can bitHuman run on the device?
Yes. Essence 2 and Expression 2 render on iPhone and iPad, Android (arm64), Mac, Linux and in browsers with WebGPU. Measured results for each device are published at docs.bithuman.ai/performance.
Does customer audio or video leave our network?
When the avatar renders on your hardware, its audio and video stay there. The conversation runs where you choose: the CLI's local conversation brain, your own speech and language services, or bitHuman's cloud voice service. With the first two, bitHuman receives usage metering only — never audio, video or conversation text. The local brain still signs in and reports usage online, so it needs a network connection; it is not part of the offline license. In the bitHuman cloud, and with the web embed, audio and conversation are processed by bitHuman and its service providers to run the session.
Is bitHuman HIPAA compliant?
HIPAA compliance is a property of your program and deployment, not of a single software component. bitHuman can be deployed so that no protected health information reaches bitHuman — on the device, on your own servers with speech and language services you control, or fully offline — and sessions that render on your hardware store no transcript with us. Healthcare deployments are set up under an enterprise agreement and review; contact us to walk through your data flows.
How does bitHuman help with GDPR and CCPA?
With on-device, self-hosted or offline deployment, your customers' conversations stay in the systems and regions you choose, and bitHuman receives usage metering only. Creating an avatar from a portrait happens in the bitHuman cloud. We do not sell your personal information, and we do not use your content to train our AI models unless you explicitly opt in.
Does bitHuman train on our data?
No. We do not use your content to train our AI models unless you explicitly opt in.
Offline
Can bitHuman run without an internet connection?
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. Essence 1 runs fully offline today on Linux (x86_64 and ARM64) and on macOS with Apple silicon. Essence 2 and Expression 2 run fully offline on Linux x86_64 (bitHuman 2.11.17 or later). 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 runs in the bitHuman cloud only. Packs start at 100,000 credits. Other self-hosted and on-device sessions check in when they start and keep rendering through a network drop of up to 5 minutes.
Which operating systems can run an offline license?
Linux PCs and terminals, and Macs with Apple silicon (the Python package, bitHuman 2.11.17 or later, on macOS). Phones and browsers stay online, and so do apps built on the Swift package: the Swift package, the Android SDK and the web embed check your credential when a session starts. Essence 1 runs fully offline today on Linux (x86_64 and ARM64) and on macOS with Apple silicon. Essence 2 and Expression 2 run fully offline on Linux x86_64 (bitHuman 2.11.17 or later). 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 runs in the bitHuman cloud only. For Windows-based terminals, talk to us.
Building an app
How do I start building?
Get an API secret on the Creator plan, then install the Swift package, the Android SDK, the Python SDK or the web embed. Each has a quickstart in the docs.
Is there an iOS and Android SDK for bitHuman avatars?
Yes. The Swift package renders Essence 2 and Expression 2 on iPhone, iPad and Mac. essence2-android and expression2-android on Maven Central render them on arm64 Android phones. Measured results for each device are published at docs.bithuman.ai/performance.
Does the avatar render on the phone or in the cloud?
With the Swift and Android SDKs, on the phone. With the web embed, in the bitHuman cloud by default, or in the browser tab with WebGPU (render=local), falling back to cloud rendering. With a LiveKit cloud avatar, in the bitHuman cloud.
Does the SDK include the voice and the AI conversation?
The Swift and Android SDKs only render: your app passes in 16 kHz speech and draws the frames. Use any speech recognition, language model and voice, or use bitHuman's managed agent through the web embed. On a Mac or a Linux PC, the bitHuman CLI's local conversation brain can run the whole conversation on the machine.
Can I use my own language model and persona?
Yes. Any OpenAI-compatible endpoint works. Set the persona in your model's system prompt or, for a managed agent, in its system_prompt.
Can I build an AI companion app with bitHuman?
Yes. bitHuman provides the companion's face, rendered in real time on the phone, on the Mac or in the browser, and you choose the voice, the language model and the persona. The companion guide in the docs walks through adding the SDK, the API secret, resampling speech, replies, interruption and closing the avatar with the screen.
What does it cost?
From 12 October 2026, API and SDK use requires the Creator plan or higher. Rendering on the device uses 2 credits per minute of active session time, talking or idle, which is about $0.02 at top-up rates. A bitHuman cloud avatar uses 4 credits per minute, and the all-inclusive managed voice chat uses 10.
Does it work offline on a phone?
No. Apps on phones and Macs need a connection to start a session, and they keep rendering through a network drop of up to 5 minutes. The web embed needs a connection throughout. 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.
What data does the SDK send to bitHuman?
Usage reports for metering, such as which session ran and for how long. They never contain audio, video, images or conversation text. The SDK also checks your API secret when a session starts. With the web embed, the conversation itself runs on bitHuman's servers.
Can I use bitHuman in a React or Next.js app?
Yes, with the iframe embed or the floating website widget. There is no npm package: the embed is an iframe in any framework, and the docs web page has a React snippet.
Avatars & models
Which model should I use?
Essence 2 for a photoreal person; Expression 2 for any character, from a person to an animal, a mascot or an object. Both render on the device, on your servers or in our cloud.
What does it cost to make an avatar?
Making your own avatar costs 500 credits (Essence 2) or 2,000 (Expression 2), about 2–2.5 hours, on the Creator plan or higher.
Where is an avatar made?
Creating an avatar from a portrait happens in the bitHuman cloud; the finished avatar then runs on your devices.