bitHuman
Avatar runtime that can render on your own CPU-only machines (no GPU) as well as in bitHuman's cloud, billed by credits per active minute.
Overview
Best for: Kiosks, on-device and cost-sensitive deployments where you want to avoid GPU bills.
At a glance
$0.02/min self-hosted on your CPU, $0.04 cloud, $0.10 all-inclusive voice. Free plan 99 credits; Free API access listed only until 12 October. Concurrency is cloud sessions on Creator. Self-hosted still needs online license check.
Audio from your agent/TTS (or bitHuman managed voice chat)
Your TTS or managed voice
Language-agnostic lip sync from audio (not explicitly verified).
No latency number published; CPU benchmark shows 1.2x to 2.4x real-time rendering on an Intel i7-13700F.
Cloud regions not published; self-hosting runs anywhere.
Vendor states usage reports contain no audio, video, images or conversation text.
Features
- self-hosted CPU rendering
- runs on iPhone, Mac, Android, browser, Linux
- survives network drops up to 5 minutes
- lip sync from any audio
- custom avatar from one photo
- LiveKit plugin
Pricing
| What | Price | Unit |
|---|---|---|
| Self-hosted (your hardware) | 2 credits ($0.02) | per minute |
| bitHuman cloud avatar | 4 credits ($0.04) | per minute |
| Managed voice chat, all-inclusive | 10 credits ($0.10) | per minute |
| Top-up | $1 | per 100 credits |
| Creator / Pro / Business / Enterprise | $20 / $99 / $299 / $999 | per month |
Credit rates at the $1 = 100 credits top-up price: self-hosted $0.02, cloud $0.04, all-inclusive voice $0.10
Free tier: Free plan: 99 credits, 1 concurrent cloud session, chat with featured avatars; page says API access on Free only 'until 12 October'.
Source: bithuman.ai
Setup
- Subscribe to Creator or higher and get an API secret.
- Create or pick an avatar and download its .imx model file.
- pip install "bithuman[expression-2]" and set BITHUMAN_API_SECRET.
- Render frames from audio locally, or use the LiveKit plugin to publish the avatar into a room.
Endpoint
https://api.bithuman.ai/v1/agent/{agent_id}/model/downloadAuthentication
BITHUMAN_API_SECRET environment variable
Quick start python
# pip install "bithuman[expression-2]"
# export BITHUMAN_API_SECRET="<your API secret>"
# curl -fL -o wise-pup.imx \
# "https://api.bithuman.ai/v1/agent/A23WJF0199/model/download?model=expression-2"
import bithuman
# Render a lip-synced avatar locally on CPU from an audio file
with bithuman.open("wise-pup.imx") as avatar:
frames = 0
for frame in avatar.render("speech.wav"):
frames += 1 # push each frame to your video sink
print(frames, "frames")
# For live agents use the LiveKit plugin (livekit-agents[bithuman])
# and start the avatar session before your AgentSession.Written from the current docs. Check the vendor's SDK version before you ship.
Warnings
Free API access has an end date
The pricing page lists Free-plan API access only 'until 12 October' (2026 presumably). Plan on Creator ($20/mo) for any API work.
Self-hosted is not offline-licensed
Even on your own CPU, sessions check credentials at start and report usage online; rendering only survives network drops of up to 5 minutes.
Idle minutes are billed
Billing counts active session time whether talking or idle, to the second.
Avatar creation costs credits and time
Expression 2 costs 2,000 credits and takes about 2-2.5 hours; Essence 2 costs 500 credits.
Intel Macs unsupported for CPU mode
CPU deployment supports x86_64/arm64 Linux and Windows 11 with Python; Intel Macs are not supported.
Plus 9 warnings that apply to all avatars and live video APIs. See category warnings.
Limits
- Concurrent cloud sessions: 1 / 3 / 10 / 50 / 200 by plan
- Self-hosted sessions not concurrency-limited on Creator+ (per page)
- A session needs network at start; offline only for up to 5 minutes
Models and products
| Name | Status |
|---|---|
| Essence 2 | GA |
| Expression 2 | GA |
| Essence 2 Max | Deprecated |
Docs and sources
Docs
Sources used
Latency, the year on the Free API cut-off, yearly prices.