○

The #1 open-source voice interface.

Get Updates‎ ‎ |‎ ‎ Documentation

We want to help you build. Apply for 1-on-1 support.

Important

This experimental project is under rapid development and lacks basic safeguards. Until a stable 1.0 release, only run this repository on devices without sensitive information or access to paid services.

The 01 is an open-source platform for conversational devices, inspired by the Rabbit R1 and Star Trek computer.

By centering this project on Open Interpreter, the 01 is more natural, flexible, and capable than its predecessors. Assistants built from this repository can:

Execute code
Browse the web
Read and create files
Control third-party software
...

We intend to become the GNU/Linux of this new space by staying open, modular, and free.

Software

git clone https://github.com/OpenInterpreter/01
cd 01/software

Not working? Read the setup docs.

brew install ffmpeg # mac only. windows and linux instructions below
poetry install
poetry run 01

Note: The RealtimeSTT and RealtimeTTS libraries at the heart of the 01 are the work of Kolja Beigel. Please star those repositories and consider contributing to those projects!

Hardware

The 01 is also a hub for hardware devices that run or connect to our software.

Mac, Windows, and Linux are supported by running poetry run 01. This starts the 01 server and a client that uses your ctrl key to simulate the 01 light.
We have an Android and iOS application under development here.
The 01 light is an ESP32-based, push-to-talk voice interface. Build documentation is here.
- It works by connecting to the 01 server.

We need your help supporting & building more hardware. The 01 should be able to run on any device with input (microphone, keyboard, etc.), output (speakers, screens, motors, etc.), and an internet connection (or sufficient compute to run everything locally). Contribution Guide ↗️

What does it do?

The 01 exposes a speech-to-speech websocket at localhost:10101.

If you stream raw audio bytes to / in Streaming LMC format, you will receive its response in the same format.

Inspired in part by Andrej Karpathy's LLM OS, we run a code-interpreting language model, and call it when certain events occur at your computer's kernel.

The 01 wraps this in a voice interface:

Protocols

LMC Messages

To communicate with different components of this system, we introduce LMC Messages format, which extends OpenAI’s messages format to include a "computer" role:

LMC.mov

Dynamic System Messages

Dynamic System Messages enable you to execute code inside the LLM's system message, moments before it appears to the AI.

# Edit the following settings in Profiles
interpreter.system_message = r" The time is {{time.time()}}. " # Anything in double brackets will be executed as Python
interpreter.chat("What time is it?") # It will know, without making a tool/API call

Guides

01 Server

To run the server on your Desktop and connect it to your 01 Light, run the following commands:

brew install ngrok/ngrok/ngrok
ngrok authtoken ... # Use your ngrok authtoken
poetry run 01 --server light --expose

The final command will print a server URL. You can enter this into your 01 Light's captive WiFi portal to connect to your 01 Server.

Local Mode

poetry run 01 --profile local.py

Customizations

To customize the behavior of the system, edit the system message, model, skills library path, etc. in the profiles directory under the server directory. This file sets up an interpreter, and is powered by Open Interpreter.

To specify the text-to-speech service for the 01 base_device.py, set interpreter.tts to either "openai" for OpenAI, "elevenlabs" for ElevenLabs, or "coqui" for Coqui (local) in a profile. For the 01 Light, set SPEAKER_SAMPLE_RATE in client.ino under the esp32 client directory to 24000 for Coqui (local) or 22050 for OpenAI TTS. We currently don't support ElevenLabs TTS on the 01 Light.

Ubuntu Dependencies

sudo apt-get install ffmpeg

Contributors

Please see our contributing guidelines for more details on how to get involved.

hirajanwin/01

○