bitHuman

Developers · Examples

Examples you can clone and run

Every example builds from a fresh clone of bithuman-examples. Each card says what it needs and whether it holds a conversation. All of them need an API secret, which from 12 October 2026 means the Creator plan or higher.

bithuman-examples on GitHubPick a platform

Gallery

Clone one and run it

  • iOS — Expression 2: a still from the recording

    iOS — Expression 2

    A SwiftUI app with a talking character, rendered on the iPhone or iPad.

    Runs on
    iPhone, iPad
    Conversation
    No: it speaks a bundled clip, or lip-syncs your microphone
    Needs
    API secret, Xcode 26, an iPhone or iPad

    swift/ios-expression2 Walkthrough

  • Screenshot coming

    iOS — Essence 2

    A photoreal person with idle motion, rendered on the iPhone or iPad.

    Runs on
    iPhone, iPad (iOS 26)
    Conversation
    No: it plays a bundled line
    Needs
    API secret, Xcode 26, a physical iPhone or iPad

    swift/ios-essence2 Walkthrough

  • Mac — Expression 2: a still from the recording

    Mac — Expression 2

    One Swift command-line tool: speech in, lip-synced frames out, on your Mac.

    Runs on
    Mac (Apple silicon)
    Conversation
    No: it renders a speech file
    Needs
    API secret, Xcode 26

    swift/macos-expression2 Walkthrough

  • Android — Expression 2 and Essence 2: a still from the recording

    Android — Expression 2 and Essence 2

    Two complete Gradle apps that render a talking avatar on the phone.

    Runs on
    Android arm64
    Conversation
    No: each renders a speech clip
    Needs
    API secret, a physical arm64 phone

    android/expression2-hello android/essence2-hello Walkthrough

  • Python quickstart: a still from the recording

    Python quickstart

    Open an avatar, play speech through it and watch it talk; conversation.py adds a voice conversation.

    Runs on
    Mac, Linux
    Conversation
    Yes, in conversation.py (with your own OpenAI key)
    Needs
    API secret

    python/quickstart Walkthrough

  • Screenshot coming

    Python with LiveKit

    A voice agent with a face: rendered on your own machine, or a bitHuman cloud avatar in your LiveKit room.

    Runs on
    Mac, Linux, LiveKit
    Conversation
    Yes
    Needs
    API secret, LiveKit, an OpenAI key

    python/self-host python/cloud-essence Walkthrough

  • Screenshot coming

    Next.js

    A browser front end for an avatar agent in a LiveKit room.

    Runs on
    Web
    Conversation
    Yes, through the agent in the room
    Needs
    LiveKit and an avatar agent (which needs an API secret)

    integrations/nextjs-ui

  • Screenshot coming

    Gradio web demo

    Talk to an avatar in the browser through a Gradio page.

    Runs on
    Web (Python)
    Conversation
    Yes
    Needs
    API secret, an OpenAI key

    integrations/gradio-web

  • Screenshot coming

    Java WebSocket

    Stream audio to an avatar server and get lip-synced frames back in Java.

    Runs on
    A Java client
    Conversation
    No: it streams audio you provide
    Needs
    API secret

    integrations/java-websocket

  • Screenshot coming

    REST API (curl and Python)

    Scripts for the REST calls: create an agent, make it speak, check your balance.

    Runs on
    Any
    Conversation
    —
    Needs
    API secret

    api/rest-api

  • CLI recipes: a still from the recording

    CLI recipes

    Render a video or run a live avatar from the terminal, with no code.

    Runs on
    Mac, Linux
    Conversation
    Yes, with bithuman run
    Needs
    bithuman login

    api/cli Walkthrough

Docs

Walkthroughs with the app running

The docs walk through the examples step by step, each with a recording of it running on a real device.

Examples in the docs Build a companion app Add the website widget