Your servers (self-hosted)

Run the CLI, Python SDK or LiveKit plugin on your own machines.

Creator plan or higherYour computer or serverNo GPU needed

What it is

The avatar renders on machines you run: a Mac with Apple silicon, or a Linux PC or server on x86_64 or arm64, including one with no GPU. You choose where the conversation runs. There is no license to buy for online self-hosting: it needs the Creator plan or higher and bills credits at the self-hosted rate.

You want	Use	Models
A talking avatar or an MP4, no code	CLI	Essence 2 and Expression 2 (`run`, `render`); Essence 1 (`run`)
Frames or MP4 clips from your own code	Python SDK	Essence 2, Expression 2, Essence 1
A voice agent in your own LiveKit rooms, rendered on your machine	LiveKit plugin with `model_path=` (guide)	Essence 2, Expression 2
The same agent in one Docker container, with your own speech-to-text, language model and voice	LiveKit self-hosted starter: opens the avatar when a person joins and closes it when they leave	Expression 2

Compare every mode: Deployment options.

Where it renders

Question	Your servers
Where the avatar renders	on your own Mac or Linux machines
Where the conversation runs	your choice: the CLI's local conversation brain, your own services, or bitHuman's
What reaches bitHuman	a credential check, the avatar download, and usage reports with no audio, video or text
Network	to start; rendering continues through a drop of up to 5 minutes

Your servers (self-hosted). Self-hosted, the avatar renders on your own Mac or Linux machine and its audio and video stay there. The conversation runs where you choose: the CLI's local conversation brain, your own services, or bitHuman's. For the rendering, bitHuman receives a credential check, the avatar download and usage reports with no audio, video, images or conversation text.

When the avatar renders on your hardware, its audio and video stay there. For the conversation, the CLI’s local conversation brain keeps speech recognition, the language model and the voice on the machine, or you bring any OpenAI-compatible language model, including one in your own network (Providers).

When you run the engine on your servers or device with your own agent, conversation text never reaches bitHuman; usage reports carry only session id, durations, product and install id. Hosted bitHuman agents store transcripts wherever the avatar renders, unless conversation logging is turned off.

Speed

Configuration	Essence 2	Expression 2
Intel Core i7-13700F (x86_64) Linux · CLI CPU only (no GPU)	2.0× real time Intel Core i7-13700F (x86_64), CPU only (no GPU) · CLI 2.8.1 · measured 2026-09-27	2.2× real time Intel Core i7-13700F (x86_64), CPU only (no GPU) · CLI 2.8.1 · measured 2026-09-27
Intel Core i7-13700F (x86_64) Linux · Python CPU only (no GPU)	1.2× real time Intel Core i7-13700F (x86_64), CPU only (no GPU) · bithuman 2.12.1 · measured 2026-10-08	2.4× real time Intel Core i7-13700F (x86_64), CPU only (no GPU) · bithuman 2.12.1 · measured 2026-10-08
Apple M4 macOS · CLI	4.2× real time Apple M4 · CLI 2.8.1 · measured 2026-09-27	8.4× real time Apple M4 · CLI 2.8.1 · measured 2026-09-27
Apple M4 macOS · Python	6.9× real time Apple M4 · bithuman 2.11.12 · measured 2026-09-25	8.4× real time Apple M4 · bithuman 2.11.12 · measured 2026-09-25

Times real time: seconds of avatar video rendered per second. At 1.0× or more, an avatar holds a live conversation. Select a figure for its release and date. All configurations and how we measure.

Price

2 credits per minute for Essence 2 and Expression 2, about $0.02 a minute at the top-up rate of $1 = 100 credits. Billing: How billing works. Every rate: Pricing and credits.

Rendering an MP4 (bithuman render, or render() in Python) bills the length of the video it writes, at the same rate.

Limits

Credential: rendering needs a credential. Sign in with bithuman login, or set BITHUMAN_API_SECRET (Your API secret).
Network: a session checks your credential when it starts and keeps rendering through a network drop of up to 5 minutes. Usage reports carry no audio, video, images or conversation text.
Sessions: self-hosted sessions are limited by credits.
Operating systems: macOS on Apple silicon; Linux on x86_64 or arm64; Windows 11 on x86_64 with Python.
Off the internet: see Fully offline.

First command

CLI

curl -fsSL https://install.bithuman.ai | sh
bithuman login                    # in CI, export BITHUMAN_API_SECRET instead
curl -fsSLo speech.wav https://docs.bithuman.ai/samples/speech.wav
bithuman render wise-pup speech.wav -o out.mp4

Python

python3 -m venv .venv && source .venv/bin/activate
pip install "bithuman[expression-2]"    # an Essence 2 avatar: "bithuman[essence-2]"
export BITHUMAN_API_SECRET="<your API secret>"
export AVATAR=$(python -m bithuman pull A23WJF0199)    # prints the avatar's local path
curl -fsSLo speech.wav https://docs.bithuman.ai/samples/speech.wav
python -c 'import bithuman, os; bithuman.open(os.environ["AVATAR"]).render("speech.wav", out_mp4="out.mp4")'

LiveKit

pip install "livekit-agents[openai,silero]" livekit-plugins-bithuman "bithuman[expression-2]" python-dotenv
export AVATAR=$(python -m bithuman pull A23WJF0199)
# pass model_path=os.environ["AVATAR"] to bithuman.AvatarSession: /build/voice-agent

Docker

git clone https://gitlab.com/bithuman/sdk/bithuman-examples.git
cd bithuman-examples/integrations/livekit-self-hosted
cp .env.example .env              # your LiveKit keys, API secret and OpenAI key
docker compose up --build

out.mp4 is the wise-pup sample avatar speaking the 15-second sample. The CLI’s ffmpeg and live-session setup is on CLI.