Getting insights with AI from meeting and lecture transcriptions

Have you ever found yourself overwhelmed with hours of lecture recordings or meeting audios, struggling to extract the crucial points or action items? The combination of AI transcription tools like Whisper and the analytical power of ChatGPT offers a solution for students and teachers. The combination of Whisper and ChatGPT enables you to transcribe audio files but also to interact with the text to extract summaries or key learning points from your lectures, or actionable items from your meetings. We begin this article by explaining the process and benefits of transcribing audio using Whisper, and how it can be beneficial in an educational setting. We will then explain the best practices for using ChatGPT to analyze these transcriptions, offering practical prompts to effectively extract the most valuable information.

How to combine Whisper and ChatGPT?

Transcribing your lectures or meetings can be done using tools like Whisper and AssemblyAI. Using Whisper for transcription can be beneficial for you as a student or teacher. Whisper saves time by automating the transcription process, instead of manually transcribing lengthy audio recordings. It can be used in practice in the following ways:

1. Note-taking during lectures: You can use Whisper to transcribe online lectures, allowing you to focus on understanding the content instead of taking extensive notes. Teachers can also benefit from this feature when recording their lectures or presentations.
2. Improved documentation and follow-up during meetings: Transcribing meetings allows you to have a detailed and accurate written record of the meeting. This makes it easier for you to track action items, decisions, and key points discussed during the meeting. This can lead to efficient follow-up, ensuring that tasks and responsibilities are properly documented and assigned. It can also be beneficial for you if you missed a meeting and can easily read back the transcripts.

Using transcription tools like Whisper or AssemblyAI for lectures and meetings results in a plain text transcript, which, while accurately capturing spoken words, lacks deeper insights or analysis. This raw text is a factual record, but it doesn’t provide interpretations, summaries, or highlight key points. To bridge this gap, you can integrate ChatGPT with well-crafted prompts. By feeding the transcript into ChatGPT with specific, targeted prompts, you can extract meaningful insights, such as identifying central themes, summarising, or getting a bullet point list of actions to be taken. This can help you revise lectures and meetings.

Prompts for getting valuable insights.

Using Whisper leaves us with a .txt file with a full transcript of the lecture or meeting, like the one in the picture below. We can open this .txt file and copy its content to ChatGPT. In the examples below we will refer to this copied text as [Transcript].

1. Making a bullet-list of deliverables.
   Below an example of this prompt can be shown for a meeting of the recruitment team at a university that discussed how to recruit new students.

You: "[Transcript] 

Make a bullet-list of the deliverables of this meeting."


ChatGPT: "The deliverables of this meeting include:

1. Create a set of personalized email templates to engage with prospective students, highlighting the university's unique selling points and programs.
2. Develop a social media content calendar with a schedule of posts, including engaging visuals and captions, to promote upcoming events and application deadlines.
3. Compile a frequently asked questions (FAQ) document for the admissions team, enabling them to provide quick and accurate responses to inquiries from prospective students.
4. Coordinate the production of a short video showcasing the university's campus, programs, and student life, suitable for sharing on the website and social media."


# Note: All output is fictional

We can also ask ChatGPT to give the deliverables in a certain format. For example, if we want to make issues out of the deliverables, we can give ChatGPT a follow- up prompt like in the iframe below. It will then readily give all deliverables in code blocks when you prompt the correct way.

2. Asking for a summary of the meeting or lecture.
   Below an example of this prompt can be shown for a meeting of this website, asking ChatGPT to make a summary of one paragraph for this meeting.

You: "[Transcript] 

make a summary of the meeting of one paragraph"

ChatGPT: "During the meeting, the team discussed various topics and action points. They scheduled a hackathon-style meeting to work collaboratively and create content efficiently, emphasizing the importance of starting to write articles and content on WordPress. The team also explored potential collaboration with student associations, to expand their reach. Technical questions were addressed, and support was offered for using WordPress. The meeting concluded with plans for future engagements and events to promote Tilburg AI and its valuable content."

# Note: All output is fictional

3. Asking for key learning points from a lecture
   For a lecture, you want to have the key learning points, filtering out all unimportant talk and only keeping the main points. After this, you can even ask follow up questions based on these focal learning points, for example to create 10 practice questions.

You: "[Transcript] 

make a bullet-list of the key learning points from this lecture"

ChatGPT: "Certainly! Here's a bullet-list of key learning points from the lecture about economic games:

1. Definition of Economic Games: Economic games are experiments designed to study human behavior in economic decision-making scenarios. They often involve strategic interactions and real or hypothetical rewards.
2. Game Theory Basics: Game theory provides the framework for analyzing economic games. It involves studying the strategies and outcomes of players in various situations.
3. Types of Economic Games: Examples include the Prisoner's Dilemma, Ultimatum Game, and Trust Game. Each game simulates different economic and social scenarios.
4. Rationality and Nash Equilibrium: Players are assumed to be rational decision-makers, aiming to maximize their utility. Nash equilibrium is a key concept where no player can improve their outcome by changing their strategy unilaterally.
5.Cooperation and Competition: Economic games illustrate the tension between cooperation and competition. Factors like trust, reputation, and incentives influence players' decisions."

You: "Based on these key learning points, come up with four example questions to practice this material"

ChatGPT: "Certainly! Here are ten example questions to help you practice the material on economic games:

1. What is the primary purpose of economic games, and how do they differ from traditional economic modeling?
2. Define Nash equilibrium and explain its significance in the context of economic games.
3. Provide an example of a well-known economic game and describe the strategic decisions that players need to make in that game.
4. How do economic games help researchers explore social preferences, and what are some common social preferences studied in these games?
5. Give an example of an economic game that illustrates the tension between cooperation and competition. Describe how trust and incentives play a role in this game."

Prompting: As shown in this article we can get great insights from our lecture or meeting transcripts, especially when the quality of the transcript is high. It does however also depend on the quality of the prompts. In this article, we have given some example prompts for this specific use case, but the result always varies with every scenario. Having good prompts and understanding the different practices that are useful to follow when prompting ChatGPT is therefore always important.