At a Glance

Name: AI meeting companion: From voice to insight
Price: Free CAD
Rating: 4.7 (17 reviews)

Create an app to capture audio (like lectures) and summarize it. You will build it using OpenAI Whisper (text to speech) and summarize with open-source LLAMA 2 LLM hosted by IBM watsonx. You will deploy the app in a serverless environment using IBM Cloud Code Engine.

Imagine you're a student who records your teacher's lecture. We have an AI app that can turn this recording into text, accurately. It also summarizes the lecture and highlights the main points.

In our project, we'll use OpenAI's Whisper to transform speech into text. Next, we'll use IBM watsonx AI to summarize and find key points. This stage couples with prompt engineering through PromptTemplate in Langchain. We'll make an app with HuggingFace Gradio as the user interface.

The AI app snapshot
The output from the LLM not only summarizes and highlights key points but also corrects minor mistakes made by the speech-to-text model, ensuring a coherent and accurate result.

A Look at the Project Ahead

Here are the key objectives for your project:

Speech-to-Text Conversion: Utilize OpenAI's Whisper technology to convert lecture recordings into text, accurately.
Content Summarization: Implement IBM Watson's AI to effectively summarize the transcribed lectures and extract key points.
User Interface Development: Create an intuitive and user-friendly interface using HuggingFace Gradio, ensuring ease of use for students and educators.
App Deployment: Learn and apply the skills necessary to deploy the application online using IBM Code Engine, making the tool accessible to a wider audience.

What You'll Need

General knowledge of Python and a browser.

Offered By: IBMSkillsNetwork

AI meeting companion: From voice to insight

At a Glance

A Look at the Project Ahead

What You'll Need