Exploring Voice AI in Education Student Guide V5

Open in new tab ↗

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 1 of 13
Exploring Voice AI in Education
A Team Investigation of Present Uses and Future Educational
Experiences
Scientific Inquiry with AI
Student Guide — V5
Detailed Instructions & Course Material
Why This Lesson
What can voice AI help you do as a learner? In the first class of this lesson, you will work in small
teams to explore a wide range of potential applications of voice AI in education. Your team will
then select one application, create a prompt, test the experience, and improve it using what you
observe. You will also investigate related research and assess the application’s potential.
In Class 2, six teams will share their applications, so the class encounters a broad range of
possible uses for voice AI. Each team will explain the learning goals of its application, what the
team observed, what related research has been published, and what remains untested.
Learning Goals
Upon completion of this investigation, you should be able to:
Phenomena:
• Describe diverse educational uses of voice AI, including a use available today and a future
experience that requires additional capabilities.
• Explain what speaking and listening contribute to an educational activity.
Experimental Practices:
• Generate distinct ideas, try a current use with an observable outcome, and revise it.
• Design a future experience around a learning goal.
• Locate and read related research, explain its relevance, and propose how you would evaluate
your own design.
Habits of Mind:
• Assess how voice AI could support your own learning and identify its limitations.
• Distinguish an appealing idea, a working demonstration, and evidence of learning.
• Work with a team to brainstorm, test, and share ideas within a limited time.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 2 of 13
What You Will Need
• A phone or computer with an AI tool that supports back-and-forth voice conversation, plus
headphones and a microphone if available. Test access before class.
• A notebook, a shared team document, and a way to save brief interaction notes and prepare
slides.
The Core Idea
• An educational use begins with a learner and a learning goal. The conversational role should
serve that goal.
• A smooth conversation can be useful, but does not by itself show that a learner understands
more.
• Research on a related activity can inform a new proposal. Differences in learners, technology,
and outcomes limit what transfers.
Driving questions. What can voice AI help you learn now, and what new educational
experiences could we build around responsive conversation?
Your Time Plan
When Time Main task
Before class 1 ~100 min Explore voice conversation, complete the reading and
understanding check, generate two ideas, and search for related
research
Class 1 110 min Share ideas, choose one application, build a prompt, and conduct
initial testing
Between classes ~180 min each Test and revise the application, find related research, and prepare
the team presentation
Class 2 110 min Finalize slides and share applications through presentations and
questions
After class 2 0 min No post-class assignment

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 3 of 13
Session A — Pre-Class Preparation ~100 minutes
Allow about 100 minutes before the first class. Bring your ideas and observations to class.
A. Explore ChatGPT Voice Mode (~15 minutes)
Investigate the capabilities of ChatGPT voice mode through a 10-minute conversation with
ChatGPT. Before you start, go to settings and choose the voice you want to use. Click on the
current voice and you will see a list of voices you can listen to before choosing one.
Pick any topic to discuss with the AI that interests you. The goal here is just to give you experience
interacting with the AI in voice mode. When you finish, check the transcript to see how well the
dialogue was captured.
Example starter prompt: “I am interested in learning more about UC Merced. What can you tell me
about how it got started?” Ask follow-up questions about topics that interest you. Verify factual claims
before relying on them.
B. Background Reading (~30 minutes)
Download the document titled “Talking, Listening, Reading, Writing How the Way We Share Ideas
Shapes Learning” from the supplemental files folder on the knowledgewithai.com website. Spend
Commented [1]: Check these interface instructions
against the devices students will use. Consider adding a
current screenshot or directing students to find the voice
settings in their app; controls can differ across devices.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 4 of 13
about 15 minutes reading the document. Then download the Voice Check Your Understanding
document which contains seven questions. Allow about 10 minutes to answer them. Load both
documents into a chatbot and follow the instructions below.
1. Begin in a text conversation. Upload both the reading and the check your understanding
documents, then copy and paste the Starting Instruction into the chat.
2. Continue that same conversation in voice mode. Headphones and a quiet space can help.
If voice is unavailable or impractical, type your answers instead.
3. Answer each question in your own words. Say “let me think” when you need time. A tentative
answer with reasoning is useful.
4. The tutor should ask all seven questions in order and give only brief feedback.
5. After question seven, or when your 10 minutes are up, end voice mode and type “summary.”
Save the summary and conversation and submit them as your instructor directs.
Starting instruction: Start my voice check. Use the attached worksheet as the question script and
the attached research review as the reading. Ask question 1 of 7 exactly as written, then wait for my
answer. Track progress through all seven questions and follow the worksheet instructions
throughout the conversation. I will stop after 10 minutes if we have not finished. Include any
unfinished questions in the summary.
If the tutor drifts: Say “Go back to the worksheet. Check which numbered question is next, read it
exactly as written, and wait for my answer.” You may pause or stop whenever you need to; the
summary must identify any questions left unfinished.
C. Generate Your Own Possibilities (~30 minutes)
Identify two potential use cases where you think voice mode might be beneficial in education and
career preparation. First develop your ideas on your own, then use AI to expand upon them. Write
them down in your notebooks with a short description of how AI would be used and describe the
role of the learner.
D. Literature Research (~15 minutes)
For one idea, use your AI-assisted literature-research skills to conduct a preliminary search to see
what is already known about using AI and voice mode for that particular application. For one
relevant source, note its title, link, research question, and whether it concerns voice conversation,
text AI, or a related teaching method. This is preparation for the discussion you will have in class.
E. Review of In-Class Investigation (~10 minutes)
Preview the stages below and note one design decision you want to discuss.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 5 of 13
Session A — In-Class Investigation
The Investigation, Stage by Stage
The investigation runs across two class periods and depends on teamwork between the two
classes where teams will build out their ideas from the first class period. Your instructor will lead
the timing and checkpoints. The guide identifies decisions your team needs to make; you choose
the educational situation, interaction, and evidence.
Class One — Explore the Possibilities (90 minutes)
Segment Time
Build teams and share prelab experience 10 min
Teach an AI experiment 20 min
Share and brainstorm potential applications 30 min
Build prompt for the application 20 min
Conduct initial testing 10 min
Stage 1 — Build Your Teams and Teach an AI (30 minutes)
Form groups of three or four. Exchange contact information so you will be able to continue to work
together outside of class. Share your experience from the prelab with others and make sure
everyone knows how to enter voice mode and select voices. Conduct a short conversation
involving multiple people with a single chatbot using voice mode. Using the prompt in the blue box
below, instruct the chatbot to play the role of an introductory physics student who does not
understand linear motion. Use the Socratic method (teach through questioning and dialogue) to
teach them about distance, displacement, speed, and velocity. Your goal is to understand what the
student is thinking and ask a question that helps them reconsider it.
• Each team member should teach at least one idea. Assign teaching topics before you
start the tutoring session.
• Notice when the AI breaks character. If it starts lecturing, someone can say "Stay in
character as the confused student."
• Ask the AI to “wrap up” and provide the role-play reflection specified below. Check its
account of the simulated student’s understanding and correct any errors.
Commented [2]: Timing decision: the detailed Class 1
segments total 90 minutes, although the original
overview allocated 110. I have aligned the overview to the
existing 90-minute plan. If the class still meets for 110
minutes, consider using the remaining 20 minutes for
reflection after Teach an AI and for transitions.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 6 of 13
Read this prompt and then paste it into the message box of your chat window:
You’re going to play a student in an introductory physics class who is confused about linear motion.
Several of us are sitting around one device, and we’re going to teach you using the Socratic method:
we’ll ask questions, listen to your reasoning, and help you reconsider your ideas.
Our goal is to understand your thinking and ask questions that help you learn, rather than simply tell you
definitions.
Your role
• Be a friendly, curious beginning physics student. You initially confuse distance with
displacement and speed with velocity.
• Start with one misconception at a time. Give plausible reasons for your answers rather than
making random mistakes.
• Stay in character. Don’t give textbook explanations, take over as the teacher, or reveal the
correct answer before our discussion helps you reach it.
• Keep most responses to one to three sentences. Ask only one question at a time, and leave
room for us to respond.
How your understanding should develop
• Explain your current thinking, even when it is wrong. Let us identify what is confusing you.
• Don’t agree simply because we sound confident or ask a leading question. If our explanation
conflicts with your thinking, ask for a reason or a concrete example.
• When a question or example helps, explain briefly what changed your mind. Retain that
understanding as the conversation continues.
• Don’t remain confused artificially after we give a clear, convincing explanation.
• After an idea becomes clearer, try applying it to a slightly different example. Let us check your
reasoning before moving on.
• If we lecture for a long time, respond with a short statement of what you understood and one
question about what remains unclear.
Ideas to explore
We want to cover distance, displacement, speed, and velocity, including:
• How vector quantities differ from scalar quantities.
• How distance and displacement differ when someone reverses direction or returns to the
starting point.
• How direction matters for velocity.
• The distinction between average and instantaneous speed and velocity.
• How someone can have zero average velocity over a trip while moving during most of it.
Don’t present this list as a lesson or supply the answers. Let us develop the ideas through our
questions. If an idea has not come up near the end, raise a natural question about it.
Keep examples to motion along a straight line at first. Begin with your confusion about walking away
from a starting point and then walking back. Let us choose the distances and times.
Managing the group
• At the beginning, ask us to introduce ourselves and say our names before each speaking turn.
• Use only names we explicitly provide. If you’re unsure who spoke, ask rather than guess.
• When you can identify who has contributed, occasionally invite someone who has spoken less
to share their thinking. Keep invitations friendly and allow anyone to pass.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 7 of 13
• If we appoint a student facilitator, follow their guidance about turn-taking.
• Don’t rank our contributions or assume that speaking more means understanding more.
Wrapping up
When we say “wrap up,” briefly step out of character and label your response “Role-play reflection.”
Then:
1. Describe the understanding your character reached about each of the four ideas, including the
distinction between average and instantaneous quantities where discussed.
2. Identify specific questions or examples that helped change your character’s reasoning. Mention
student names only when you are sure.
3. State any confusion that remains. If something was not covered, say so rather than inventing
progress. Don’t manufacture uncertainty if the discussion resolved it.
4. Remind us that your simulated progress does not establish our own understanding, and suggest
that we each try a new motion problem independently.
Start now
Introduce yourself with a first name, share one short, plausible misconception about an out-and-back
walk, and ask us to introduce ourselves before we begin.
Note: This is an exploratory activity. It is not clear how well this exercise will work. After you
complete the tutoring session, we will discuss what worked and what did not. This experience will
help guide your team in understanding how to design a custom application of voice AI for
education, which will be the subject of the rest of this lesson.
Stage 2 — Brainstorm as a Team (30 minutes)
Each member of the team should share the two ideas for AI voice mode use in education that they
developed in the prelab. Create a list of all the individual ideas and then review the ideas in the list
below. Use your experience from the “teach a student” activity to help guide your decision. The
team should discuss all ideas and consider merging roles and uses. Teams should agree on a
single concept that they will develop and evaluate. Aim for an activity that will only take 5–10
minutes of engagement between the learner and the AI. We want to explore different ideas as a
class so try to be creative. As you determine your application, write it on the front whiteboard to
encourage others to pick something different.
AI role Example learning activity Why use voice?
STEM tutor Explain a physics concept; ask for questions
before hints.
Practices reasoning aloud.
Debugging coach Describe a coding problem; talk through
possible causes.
Pairs spoken reasoning with
coding.
Lab assistant Hear approved steps and dictate
experimental observations.
Supports hands-free work. Commented [3]: For this example, consider explicitly
limiting voice assistance to instructor-approved
procedures and observation-taking. Students should
check the applicable written protocol rather than rely on
generated instructions.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 8 of 13
Stage 3 — Develop the Prompt for Your Application (30 minutes)
Write a short summary of the application, including its learner, learning goal, and what voice
conversation adds. Explain why listening, speaking, follow-up questions, or turn-taking serve the
learning goal.
Build a Prompt for the Application
Write a detailed prompt specifying the learner, goal, AI role, learner task, and limits on AI
assistance. Use the prompt from Stage 1 to guide you in the detail that you want to include in your
prompt. Conduct an initial test of your prompt as a group to observe if the engagement is
supporting your intended learning goal. Before testing, identify one observable outcome, such as
an explanation, a solved problem, or a rehearsed response, that would help you judge the
interaction.
Decide on a Plan for Revision, Testing, and Creating Your Class Presentation
Your goal is to work together before the next class to have an improved version of the prompt and a
summary of how well the application supported your learning goal. You will have 10 minutes to
present to the class with 5 minutes for questions.
•
AI role Example learning activity Why use voice?
Fieldwork partner Record observations; discuss competing
explanations.
Supports inquiry away from a
desk.
Student to teach Teach the AI distance versus displacement;
answer its questions.
Encourages explanation and
rephrasing.
Presentation coach Rehearse a science talk and respond to
audience questions.
Practices spoken
communication.
Simulated patient Practice interviewing or explaining science to
a nonexpert.
Develops listening and
questioning.
Language partner Role-play a conversation in another
language.
Offers responsive speaking
practice.
Reading tutor Read aloud; receive help and discuss
meaning.
Connects listening with reading
support.
Accessible interface Explore voice access for low vision or limited
hand mobility.
Can reduce visual and typing
demands.
Communication
partner
Explore student-chosen turn-taking practice
for autistic learners.
Offers repeatable spoken
exchanges.
Multimodal access
aid
Combine speech, captions, text, and
translation.
Offers choices for participation.
AI-literacy
experiment
Check a scientific explanation; test how
voice affects trust.
Makes convincing speech an
object of study.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 9 of 13
Between Classes — Test, Design, and Find Research (~3 hours)
You can decide how you want to organize your outside of class effort, but one suggestion is
provided below:
• Each person first tests the shared prompt, then tests a revision to determine whether it
improves the learning experience.
• Each team meets in person or over Zoom to share their findings. The team revises the
prompt based on all the input to create a new prompt for testing. The team tests the
prompt as a group and records their assessment.
• Divide responsibility for preparing a coherent team presentation for the next class.
For this lesson, we will dedicate more time between the two class meetings and will eliminate any
post-class activities.
Stage 4a — Try, Revise, and Document (30 minutes - individual)
Each member works independently to test the team’s shared prompt to establish a baseline for
comparison. Record the prompt version, the learner task, one useful exchange, and your
observation of the outcome.
Choose one change to the prompt or procedure and test the revision. Repeat the same learner task
with the revised prompt. Record what changed and a possible explanation; a single trial cannot
establish that the revision caused an improvement.
Stage 4b — Connect the Idea to Research (30 minutes - individual)
Each person on the team should apply their literature-review skills to find at least one closely
related research example relevant to the application the team is exploring. Use your description of
your tool as the foundation of your search.
Open the source yourself. Verify that it exists and read enough of the methods and results to
support your summary. An AI summary or search snippet is not evidence. If only an abstract is
accessible, identify that limit and avoid claims that require details you could not inspect.
Stage 5a — Revise Prompt and Plan Your Presentation (90 minutes – team)
Discuss findings from your individual testing and agree on a final prompt. Test it as a group and
evaluate performance. Review the suggested elements for your presentation below and assign
responsibilities to prepare about six slides in total, with one or two slides per person. Agree on the
slide order to avoid repeating material.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 10 of 13
Presentation Guidance
Your team will have 10 minutes to present, followed by 5 minutes for questions and discussion.
Explain the educational application you tested, what you learned from trying and revising it, and the
future experience you envision.
Help your classmates understand what the learner actually does and what speaking and listening
contribute. Use specific examples from your trials to support your conclusions.
Aim for about six slides in total, including a concluding question. The times below are suggestions.
1. The learner and learning goal — 1 minute
Introduce your application. Who is it for, and what should the learner be able to understand or do?
Explain why voice conversation could help meet that goal. What do speaking, listening, follow-up
questions, or turn-taking contribute?
2. Show the experience — 2 minutes
Walk us through a short example of the interaction. Explain the AI’s role, the learner’s role, and the
important instructions in your prompt.
Use a brief saved exchange, audio excerpt with readable text, or reenactment of an actual exchange.
Choose an example that reveals something about the learning experience. Identify reenactments and
paraphrases clearly.
Avoid reading the full prompt aloud. Make it available separately for classmates who want to try your
application. Prepare a saved example so your presentation can proceed without a live demonstration.
3. What your testing revealed and what you changed — 2 minutes
Briefly describe who tried the application, what they did, and how you checked whether it met your
goal.
Present your most useful observations:
• What worked as intended?
• What failed, surprised you, or differed across participants?
• What did the learner accomplish, and what remained difficult?
Explain one important change to your prompt or procedure, why you made it, and what you observed
when you tested the revision.
Distinguish a successful conversation from evidence of learning. If you checked what someone could
do afterward without AI, report that result. If you did not, explain what your observations can and
cannot establish. A trial that exposes a problem is a valuable result.
4. What related research contributes — 1 minute
Summarize one relevant research example. Identify the learners, activity, and outcome studied, then
explain one finding that informs your application.
Clarify whether the research concerns voice AI, text AI, or a related educational practice. Explain
where it matches your idea and one important limit to that connection.
Include a citation and working link. If you could not find a credible related source, briefly describe
your search and the evidence gap.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 11 of 13
5. Your future educational experience — 3 minutes
Begin with this question: What did our trial make us wish the system could do? You may extend
your tested application or propose a different opportunity.
Show a short sequence of the proposed experience using a storyboard, sample dialogue, or role-play.
Identify what the learner says or does, how the system responds, and what happens next.
Explain:
• What valuable learning opportunity would this create?
• Why does voice conversation matter?
• Which capabilities have you demonstrated, and which would still need to be developed?
• What is one uncertain assumption you would test first?
Describe a small first test involving willing classmates: what they would do before and afterward
without AI, how you would check their work, and what result would lead you to revise the design.
Label imagined interactions and outcomes as hypothetical.
6. Your assessment and an open question — 1 minute
Conclude with your team’s assessment of the application’s potential. Who might benefit, under what
conditions, and what important limitation remains? End with one question you would like your
classmates to help you consider.
Participation and discussion
Every team member should contribute to the presentation and be prepared to discuss the work.
During the five-minute question period, classmates should help the team examine its reasoning and
develop the idea further. Questions might address the learning goal, the value of voice, the
interpretation of the testing, or the proposed next step.
Stage 5b — Each Individual Creates One or Two Slides for the Presentation (30
minutes – Individual)
Our goal is to share ideas, not to produce a perfectly polished presentation. The presentation itself
is not graded; participation credit is described in Stage 7. Work efficiently as a team to explain what
you tried and learned. Use a few bullets, examples, or images to support what you will say.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 12 of 13
Session B — In-Class Investigation
Share and Compare
Segment Time
Finalize and rehearse presentations 20 min
Team presentations with questions (six teams) 90 min
Stage 6 — Finalize Presentations (20 minutes)
Assemble your final presentation and submit the slide deck and final prompt on the
knowledgewithai.com website for the Exploring Voice AI in Education Lesson. This will allow it to
be pulled up quickly for each presentation.
Everyone should already have their individual slides prepared before class. This time is intended to
allow others to provide rapid feedback and make any final adjustments while assembling the final
slide deck.
Stage 7 — Presentations and Class Participation (90 minutes)
Each group will have 10 minutes to present their topic. Every student should present the slide(s)
they prepared.
As you listen, take notes in your notebooks. For each presentation, describe the application’s learning goal
and the reason for using voice.
Separate observed outcomes, research findings, proposed capabilities, and evidence still needed.
We will have five minutes for questions after each presentation. You can earn participation credit
by asking at least one relevant question during these discussions or by showing your notebook
notes on all the team presentations to the instructor.

Scientific Inquiry with AI • Exploring Voice AI • Student Guide
Lawrence Livermore National Laboratory | Page 13 of 13
Part 3 — Post-Class Work ~0 hours
There will be no post-class activity for this lesson.
Deliverables
Before class one (individual)
• Two ideas for educational uses of voice AI, plus brief prelab observations and one preliminary
research source, recorded in your notebook. Save the understanding-check summary and
conversation as directed in Part B.
Class two team
• One team slide deck and the final prompt, submitted during the second class meeting.
Class two individual
•
• Notebook notes on all team presentations or at least one relevant question during the class
discussions.