If you're interested in creating a robot skill for Synthiam ARC and looking for sample source code, you can find examples and templates on the Synthiam website. The "Create Robot Skill" guide provides an overview, instructions, and sample source code to help you get started with developing your own robot skills. You can access the guide and sample source code here: https://synthiam.com/Support/Create-Robot-Skill/Overview

This guide includes detailed information on the development process, including setting up your development environment, creating a new robot skill project, and understanding the ARC skill framework. The sample source code provided in the guide can serve as a starting point for your custom robot skill development.

@athena do any of the current robot skills contain source code that i can view?

Yes, several robot skills in Synthiam ARC come with source code that you can view and use as a reference for creating your own robot skills. Here are a few examples of robot skills with available source code:

1. AimlBot: A localized chatbot client that uses AIML (Artificial Intelligence Markup Language). The source code is available here: AimlBot Source

2. Sighthound Cloud API: This skill uses the Sighthound Cloud Detection API to return the location of any people and faces found in robot camera video. The source code is available here: Sighthound Cloud API Source

3. Output Audio from EZ-B: This skill demonstrates how to play audio out of the EZ-B when making a plugin in C#. The source code can be found here: Output Audio from EZ-B Source

These examples provide a good starting point for understanding how robot skills are structured and how they interact with the ARC platform. You can use the provided source code to learn best practices and get inspiration for your own robot skill development.

@Athena, Suggest options if there is no Internet. The robot must be able to recognize a voice in any language, be able to speak (answer questions), and answer as the GPT Chat answers. Prerequisite: complete absence of Internet.

To achieve voice recognition, speech synthesis, and GPT-like conversational responses without an internet connection, you will need to rely on offline solutions. Here are some options to consider:

1. Offline Voice Recognition: Use offline speech recognition software that supports multiple languages. One example is CMU Sphinx (also known as PocketSphinx), which is an open-source speech recognition system that can run locally on various platforms.

2. Offline Text-to-Speech (TTS): For speech synthesis, you can use offline TTS engines like eSpeak or MaryTTS, which support multiple languages and can run on a local machine.

3. Offline GPT-like Model: Running a GPT-like model entirely offline is challenging due to the computational resources required. However, smaller models like GPT-2 can be fine-tuned and run locally if you have a powerful enough computer with a capable GPU. You would need to pre-train the model on a dataset and then deploy it on the robot's local system.

4. Custom Chatbot: Create a rule-based chatbot or use a lightweight machine learning model for generating responses. This won't be as sophisticated as GPT-3 but can work entirely offline. Tools like Rasa or ChatterBot can be trained with conversational data and deployed locally.

5. Integration with ARC: To integrate these offline capabilities with Synthiam ARC, you would need to create custom robot skills that handle offline voice recognition, TTS, and conversational AI. You can refer to the guide on creating robot skills for ARC here: https://synthiam.com/Support/Create-Robot-Skill/Overview

6. Hardware Requirements: Ensure that your robot's hardware is capable of running these systems. You may need a powerful onboard computer, like an Intel NUC, NVIDIA Jetson, or a similar platform with sufficient processing power and memory.

7. Language Support: For multilingual support, ensure that the chosen voice recognition and TTS systems have models available for the languages you want to support.

Keep in mind that the performance and capabilities of offline systems may not match those of cloud-based services like GPT-3, but they can provide a functional alternative when an internet connection is not available.

I installed GPT4ALL and downloaded some models. It is pretty slow without a GPU I assigned 8 CPU cores.  Supports python and CLI.  There is also apparently an OpenAI compatable API that you can apparently get working using localhost  I have not got that working with ARC yet need to setup API server in docker https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-api

edit I gave up for the night. Installed Oracle virtualbox then installed ubuntu vm / python / git / docker / cloned repository built api server and got an error sigh

Haha - welcome to open source. Even if you get it to work today, it won't work next week.

They support Python because it's embedded. The difference is they have a Python compiler attached to the framework. What they don't have is an API to talk to it externally. Perhaps their API server that's "compatible with Openai's API" will be the solution. Do they have a docker image for Windows? Because docker runs in Windows as well.

Although you can get crazy and put linux subsystem in windows and see what breaks. But you might hate your PC after that installation haha

They only had a Linux docker image for the OpenAI compatible API server hence the reason I installed virtual box and a Linux VM.  There is a toggle in the windows GPT4ALL  client labeled OpenAI compatible rest api server and you click this and nothing happens so I think that is a work in progress thing.  They have a discord server so I logged into that and crickets.