This Project is an Generative AI Chat bot that answer to your requests in both text & Speech. Built on Serverless architecture, using Aws Lambda, This application uses the power of Amazon polly to Synthesis Speech from text.
You can find the architecture diagram for this project in the architecture directory.
-
Frontend Interaction:
- User interacts with the frontend interface, such as a chat window or input field.
- Frontend sends HTTP requests to the OpenAI API endpoint, including the user's message.
- OpenAI API processes the request and generates a response based on the input message & sends back the response to the frontend.
- Frontend sends HTTP requests to the AWS API endpoint, including the response received from OpenAI.
-
Communication with AWS Backend (Serverless Architecture):
- API receives the response from the frontend and processes it.
- API sends request to AWS lambda to generate an audio file from the text response using Amazon Polly.
- Upon successful generation of the audio file, a response including the URL of the audio file stored in S3 Bucket to the frontend.
-
Audio Playback in Frontend:
-
Frontend receives the URL of the audio file as Response, plays the audio file directly from the provided URL.
-
b0fafea0-d6e8-11ee-a06c-7330774cd916.mp4
- AWS Lambda
- Amazon Polly
- Amazon S3
- Node js
- Python
- Streamlit(For frontend)