README.md

Empathic Voice Interface | Chat History

Fetch Chat Events, Generate a Transcript, and Identify Top Emotions

Overview

This project demonstrates how to:

• Retrieve all chat events for a specified Chat ID from Hume's Empathic Voice Interface (EVI) using the TypeScript SDK.
• Parse user and assistant messages to produce a formatted chat transcript.
• Compute the top three average emotion scores from user messages.

Key Features:

• Transcript generation: Outputs a human-readable .txt file capturing the conversation between user and assistant.
• Top 3 emotions: Identifies the three emotions with the highest average scores across all user messages.

Prerequisites

Ensure your environment meets the following requirements:

• Poetry: Version 1.7.1 or higher

Check versions on macOS:

poetry --version

If you need to update or install Poetry, visit the official Poetry website.

Setting up credentials

• Obtain Your API Key: Follow the instructions in the Hume documentation to acquire your API key.
• Create a .env File: In the project's root directory, create a .env file if it doesn't exist. Add your API key:

HUME_API_KEY="<YOUR_API_KEY>"

Refer to .env.example as a template.

Specifying the Chat ID

In the main function within main.oy, set the CHAT_ID variable to the target conversation ID:

async def main():
    # Replace with your actual Chat ID
    CHAT_ID = "<YOUR_CHAT_ID>"
    # ...

This determines which Chat's events to fetch and process.

Installation and usage

1. Install dependencies:

poetry install

2. Run the project:

poetry run python main.py

What happens when run:

• The script fetches all events for the specified CHAT_ID.
• It generates a transcript_<CHAT_ID>.txt file containing the user and assistant messages with timestamps.
• It logs the top 3 average emotions to the console:

Top 3 Emotions: {'Joy': 0.7419108072916666, 'Interest': 0.63111979166666666, 'Amusement': 0.63061116536458334}

(These keys and scores are just examples; the actual output depends on the Chat's content.)