[][https://www.linkedin.com/in/ben-kahl/]

FishAI

A fully fledged AI powered assitant running on a Big Mouth Billy Bass! FishAI runs a web based configuration and testing site alongside a voice powered response pipeline all on a Raspberry Pi 4b. It utilizes Picovoice Porcupine for wake word detection, Picovoice Leopard for speech to text transcription, Google Gemini Flash 2.5 for responses, and ElevenLabs for voice synthesis.

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. License
6. Contact
7. Acknowledgments

About The Project

This is a silly little summer project that I got the idea for after seeing GPTARS.ai on Youtube make this and stumbling across a Big Mouth Billy Bass at a thrift store. As his code and process aren't available online, I decided to make my own open-source version.

(back to top)

Built With

• Python
• Google Gemini
• Picovoice
• Elevenlabs
• A Fish

(back to top)

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Prerequisites

To get started, you'll need a few hardware and software components

Hardware

• Rasberry Pi (I used a 4b 2gb, but it should work on anything newer than a Pi 3)
• Big Mouth Billy Bass (Or a animitronic of your choice)
• Microphone (I used a INMP441 MEMS mic, but a usb mic should work too)
• 2 H-Bridges
• 9 volt battery/battery pack
• Jumper wires for connecting everything together

Software

• The latest version of Raspbian
• Python 3

Installation

1. Get API keys for Google Gemini, ElevenlabsAI, and Picovoice
2. Clone the repo

   git clone https://github.com/ben-kahl/FishAI.git

3. Everything you need software-wise is included in requirements.txt, so go ahead and pip install that as shown below. pip

pip install -r requirements.txt

4. Enter your API keys in your own .env

   ELEVENLABS_API_KEY=<YOUR_ELEVENLABS_API_KEY>
   GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>
   PICOVOICE_API_KEY=<YOUR_PICOVOICE_API_KEY>

5. Change git remote url to avoid accidental pushes to base project

   git remote set-url origin <your_github_username>/<your_repo>
   git remote -v # confirm the changes

(back to top)

Usage

To start the project, run the following command

   python main.py

(back to top)

Roadmap

• [O] Voice to Audio AI response Pipeline
• [In-Progress] Website to configure settings and manually input queries
• [In-Progress] Fully fledged fish speech and listening animations

See the open issues for a full list of proposed features (and known issues).

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Contact

Ben Kahl - linkedin-url

Project Link: https://github.com/ben-kahl/FishAI

(back to top)

Acknowledgments

• Thank you to GPTARS.ai for the idea!

(back to top)