Real-time

Live talking faces — not pre-rendered

Real-time facial animation from a single portrait. Self-hostable on NVIDIA GPUs and Apple Silicon (M3+).

Start creating with Expression View docs

41-45 FPSreal-time on M3 / RTX 4090
On-deviceGPU or Apple Silicon
Self-hostableyour infrastructure

Real-time conversations

Smooth, responsive lip-sync fast enough to hold a live back-and-forth.

Stable motion

Cuts flicker and jitter that make avatars feel synthetic.

Beyond lip-sync

Head motion, expression, and speech-driven emotion — not just mouth movement.

Runs on your terms

Self-host on your own hardware, or use our managed cloud — your call.

Quickstart

Pass any portrait as the identity, grab an API secret, stream real-time animation.

# pip install bithuman
import asyncio
from bithuman import Bithuman

async def main():
    # Expression takes any portrait as identity and generates expressions on-device.
    bh = Bithuman(
        api_secret="YOUR_API_SECRET",
        model="expression.imx",
        identity="portrait.jpg",
    )
    async for frame in bh.speak("Hello, I'm an Expression avatar."):
        # Real-time RGB frame on NVIDIA GPU or Apple Silicon (M3+)
        handle(frame)

asyncio.run(main())

See full docs

Technical details

Flow matching

Learns a smooth path from a still portrait to natural facial motion in a few steps — not many trial-and-correct passes — giving fast, stable results.

Performance

41-45 FPS on modern GPUs and Apple Silicon (M3+), with extra headroom from flow matching's few-step generation.

Use cases

Live conversation agents
Customer support avatars
Talking video with real-time delivery

Build with bitHuman Expression

Ship your first character in minutes — from local prototype to production at scale.

Start creating with Expression