https://github.com/technologiestiftung/kiezbot

our little kiezrobot
https://github.com/technologiestiftung/kiezbot

Last synced: 30 days ago
JSON representation

our little kiezrobot

• Host: GitHub
• URL: https://github.com/technologiestiftung/kiezbot
• Owner: technologiestiftung
• License: mit
• Created: 2023-03-31T08:31:30.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-06-08T00:21:15.000Z (7 months ago)
• Last Synced: 2024-06-11T18:21:11.544Z (6 months ago)
• Language: Python
• Size: 1.7 MB
• Stars: 1
• Watchers: 5
• Forks: 1
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

README

        
# set autostart on raspbian

cd .config/autostart

touch kiezbot.desktop

nano kiezbot.desktop

[Desktop Entry]

Type=Application

Name=kiezbot

Exec=cool-retro-term --fullscreen -e /home/pi/Code/kiezbot/start.sh

# install dependencies

`python3 -m pip install -r requirements.txt`

# create entry for desktop start menu

cd .local/share/applications

touch kiezbot.desktop

nano kiezbot.desktop

[Desktop Entry]

Type=Application

Name=kiezbot

Terminal=false

Type=Application

Categories=Application

Exec=cool-retro-term --fullscreen -e /home/pi/Code/kiezbot/start.sh

# libs to install

`sudo apt install mpg123` (mp3 player for Linux)

`sudo apt-get install python-rpi.gpio python3-rpi.gpio` gpio lib

![](https://img.shields.io/badge/Built%20with%20%E2%9D%A4%EF%B8%8F-at%20Technologiestiftung%20Berlin-blue)

[![All Contributors](https://img.shields.io/badge/all_contributors-0-orange.svg?style=flat-square)](#contributors-)

# Kiezbot Berlin

Our little Kiezbot Berlin is a conversational AI robot simulating three different characters. It's made to interact with the citizens of Berlin to **explain AI** in a playfull way.

We use a Python script to send a voice recording of user to multiple Artificial Intelligence (AI) APIs:

- [Whisper AI](https://openai.com/research/whisper) for speech-to-text

- [ChatGPT 3.5](https://platform.openai.com/docs/models/gpt-3-5) as LLM that generates an answer

- [Google Text-To-Speech](https://cloud.google.com/text-to-speech) to let the answer sound like a real character

## Setup Environment

To install the requirements (globally) run:

`pip install -r requirements.txt` to install missing requirements

Create a `.env` file and add your API Keys like this:

`OPENAI_API_KEY="your-key"`

**Run:** `python main.py`

That's it!

## Data Flow and Services

![Data Flow and Services](./img/THE-robot.svg)

## Credits

  

    

      Made by 

        


        


        

      

    

    

      A project by 

        


        


        

      

    

    

      Supported by