Opening Question

Before we get into audio production — a quick gut check on podcasts and AI.


Have you ever listened to a podcast and wondered if any part of it was AI-generated?

Yes — there was something off about the voice or writing
Maybe — some scripts sound a little too polished or generic
No — I never thought about it
I don't really listen to podcasts

Discussion: Today we're going to use AI to research and script a podcast segment. By the end of class, you'll have the tools to do this — and the critical eye to tell when someone else didn't do it very well.

Research with AI

Before you can script a podcast, you need something worth saying. AI can dramatically speed up the research phase — but the tool you use matters.


Tool Spotlight

NotebookLM — AI That Reads Your Sources

Most AI tools are trained on the open web and can hallucinate facts confidently. NotebookLM is different: you upload your own source documents, and it only answers from those. That makes it far more reliable for research you're going to publish or broadcast.

1

Upload your sources — articles, PDFs, transcripts, or notes

2

Ask it questions and it answers only from what you gave it

3

Every answer is cited back to your source — no hallucinations

4

Use it to pull key quotes, summaries, and discussion questions


Two Research Modes — Know the Difference

Source-Grounded Research (NotebookLM)

You upload specific documents — a research report, a transcript, a policy brief, news articles you've already verified. The AI synthesizes only from those materials. It can't make up facts because it doesn't have access to anything else. This is the right choice when accuracy is non-negotiable — journalism, PR, broadcasting.

Best for: Pulling key facts from a document you trust. Generating interview questions from a topic brief. Creating episode outlines from existing research. Summarizing long transcripts into usable notes.

The key advantage: When NotebookLM cites something, you can click the citation and see exactly where it came from in your source. That's verifiability you don't get with open-web AI tools.
Open-Web Research (ChatGPT, Claude, Gemini)

These tools are trained on large amounts of internet text and can give you broad overviews, brainstorm angles, and suggest what to research. But they can also confidently invent statistics, misattribute quotes, or describe events that didn't happen. The output sounds authoritative even when it's wrong.

Best for: Brainstorming episode angles or interview questions. Understanding the general shape of a topic before you do real research. Getting ideas for what sources to look for.

The rule: Never use open-web AI output as a primary source. Every fact, statistic, or quote it gives you needs independent verification before it goes into a script.
Using AI to Structure Your Research

Once you have solid source material, AI becomes a powerful organizer. Paste in your verified notes and ask it to help you build a narrative arc — an opening hook, the main argument, a counterpoint, a closing call-to-action. The structure is AI-assisted; the facts are yours.

Here are my research notes on [topic]. Help me organize them into a podcast episode outline with: an opening hook that poses a question, three main points that build on each other, and a call-to-action at the end. Don't add any facts that aren't in my notes — mark any gaps as [RESEARCH NEEDED]. [paste your notes here]

Why this works: You're using AI for what it's genuinely good at — structure and flow — while keeping human-verified facts as the input. The AI organizes; you verify.


What NotebookLM Can Generate from Your Sources

Upload your research documents and ask for any of these:

Episode Outline

"Based on these articles, give me a 5-segment outline for a 15-minute podcast episode. Include a hook, main points, and a closing question."

Interview Questions

"From this briefing document, write 8 interview questions that go from broad context to specific details. Include one follow-up for each."

Key Facts Summary

"Pull the 10 most important facts from these documents. List them as bullets. Cite which document each fact came from."

Discussion Hooks

"What are the three most surprising or counterintuitive findings in these sources? Write each as a one-sentence hook I could open a segment with."

Writing for the Ear

A podcast script is not a news article read aloud. Writing for audio is a completely different skill — and AI needs specific instructions to do it well.


How Audio Writing Is Different

Element Written Copy (Web, Print) Audio Script (Podcast, Radio)
Sentence length Can be long and complex — reader can re-read Short. One idea per sentence. Listeners can't rewind their attention.
Numbers & stats "The study found a 34.7% increase over 18 months." "The study found a jump of about a third — in under two years."
Signposting Headers and subheads guide the reader You have to say it out loud: "Let's talk about why that matters…"
Punctuation Follows grammar rules Written for breath and pause — dashes and ellipses are tools
Word choice Formal vocabulary is fine Use words you'd actually say in a conversation — nothing you'd stumble over
Transitions Visual — a new paragraph or section break Must be spoken: "Coming up next…" / "Here's what's interesting…"

Prompting AI for Audio Scripts

The single most important instruction you can give an AI when scripting for audio: tell it to write for the ear, not the page. Here's what that looks like in practice.

Weak prompt — what AI produces without audio instructions
Weak Prompt
Write a podcast intro about the rise of college athletics media coverage.

What you get: A dense paragraph written like a news article or Wikipedia entry. Long sentences. Formal vocabulary. No natural pauses. Nobody talks like that — and nobody wants to listen to it.

"Welcome to today's episode, where we will be exploring the multifaceted evolution of college athletics media coverage, a topic that has significant implications for sports journalism, broadcasting, and the broader media landscape..."

That sentence is 33 words before it says anything meaningful. On audio, your listener mentally tuned out at word 15.

Strong prompt — giving AI the audio instructions it needs
Strong Prompt
Write a 60-second podcast intro for a show about college athletics media coverage. Write for the ear, not the page. That means: - Short sentences. One idea each. - Conversational vocabulary — words you'd say out loud, not read on a screen. - Round any numbers (not "34.7%" — say "about a third"). - Use pauses intentionally — mark them with an em dash or ellipsis. - Open with a question or a surprising fact that makes the listener lean in. - No formal transitions like "Furthermore" or "In conclusion." Tone: energetic and direct, like a sports broadcaster, not a news anchor.

What you get: Something that actually sounds like a human being talking. Shorter sentences. Natural rhythm. A hook at the top. Something a student could actually record in class without stumbling.

The double-column script format

Professional audio scripts use a two-column format: production notes on the left, spoken words on the right. You can ask AI to generate this format directly.

Write a 2-minute podcast segment in two-column script format. Left column: production notes (music cues, pauses, emphasis notes, sound effects). Right column: spoken script only — conversational, short sentences, written for audio. Topic: [your topic here] Tone: [your tone here]

This format makes it easy to hand a script to a host who's never seen it — they know exactly when to pause, when to emphasize, and what to say.


The Podcast Production Workflow

Phase 1 — Research

Upload sources to NotebookLM

Let it extract key facts, surprising details, and potential discussion angles. Verify anything you plan to say on air.

Phase 2 — Structure

Build your outline with Claude or ChatGPT

Paste your verified notes. Ask for an episode outline with a hook, 2–3 segments, and a closing call-to-action.

Phase 3 — Script

Write for the ear — then record

Prompt for audio-ready copy. Read it aloud before you record — if you stumble, rewrite. Your mouth is the final editor.

The rule for audio: If you can't say it comfortably out loud, it's not ready. Read every AI-generated script aloud before you record. Your mouth will catch what your eyes miss.

Podcast Prep

This is where the lesson becomes your first real deliverable. Your team will use AI to research your angle, build an episode outline, and write a script — all in one class period.


Before you start: Confirm your team number and your approved AI & Ethics angle. If your angle has not been approved by your instructor, stop here and get that confirmation first. Enter your team number below — it will appear on every prompt you generate.

Class Period Timeline — 90 Minutes

Phase 1 · 0–25 min
Research
Upload sources to NotebookLM · Extract key facts · Identify your episode angle
Phase 2 · 25–55 min
Outline
Build episode structure · Assign segments · Generate interview questions
Phase 3 · 55–85 min
Script
Write for the ear · Edit aloud · Enter into teleprompter

Final 5 minutes: one team reads their intro aloud for the class.


Phase 1 · Research
Research Lead runs NotebookLM · All team members follow along

Upload your sources and extract what you need

Your Research Lead opens NotebookLM at notebooklm.google.com and creates a new notebook. Upload all four source files your team prepared before class. Then run the prompts below — one at a time — and share results with your team.

Choose a research prompt to generate

↑ Choose a prompt type to generate it.

NotebookLM Prompt

Research Lead: Copy each prompt into NotebookLM's chat window. Paste the results into a shared Google Doc so all five team members can read them simultaneously. Your Angle Editor decides which facts and hooks make it into the outline.

Phase 2 · Outline
Angle Editor leads · Script Writer drafts · whole team reviews

Build your episode structure in Claude or ChatGPT

Take your research results from Phase 1 and paste them into Claude or ChatGPT. Your Angle Editor enters your approved topic and the key facts your team selected. Use the prompt below to generate a timed episode outline.

Choose an outline prompt to generate

↑ Choose a prompt type to generate it.

Claude / ChatGPT Prompt

Angle Editor: Review the outline before the team moves to Phase 3. Every segment needs a clear purpose. If two segments say the same thing, cut one. If a segment has no facts behind it, flag it now — don't script something you can't support.

Phase 3 · Script
Script Writer drafts · Audio Editor reads aloud · Producer enters into teleprompter

Write your 60-second intro — for the ear, not the page

Your Script Writer takes the approved outline and uses the prompt below to generate an audio-ready intro script. The Audio Editor reads it aloud immediately. Anything that causes a stumble gets rewritten before it goes into the teleprompter.

Choose a script prompt to generate

↑ Choose a prompt type to generate it.

Script Prompt — Claude / ChatGPT


Audio Editor Checklist — Before the Teleprompter

The Audio Editor reads the script aloud and checks every item before the Producer enters it into the teleprompter at susquweb.com/teleprompter.

Read every sentence aloud

If you stumble on a word or run out of breath, stop — that sentence needs to be rewritten, not rehearsed past.

Cut sentences over 20 words

One idea per sentence. Long sentences lose listeners. If it can be two sentences, make it two sentences.

Replace every number with words

"47.3%" → "nearly half." "18 months" → "a year and a half." Numbers that read fine on paper often stall on audio.

Mark one intentional pause

Find the moment in your intro where silence lands harder than words. Mark it with a dash —. Actually pause there when you record.

Remove any AI-isms

Delete "delve," "landscape," "tapestry," "vital," "revolutionary," and any sentence that starts with "In today's world." These are AI defaults, not your voice.

End with a question or forward motion

Your intro should make the listener want to keep listening. Close with a question, a tension, or a promise of what's coming — not a summary of what they just heard.

Teleprompter handoff: Once the Audio Editor approves the script, the Producer copies the final text into the teleprompter at susquweb.com/teleprompter and sets the scroll speed. Your team is now ready for the recording suite.

What your team leaves class with

Research summary

Key facts, opening hook, and research gaps from NotebookLM — saved in your shared Google Doc.

Episode outline

Timed segment structure with interview questions and a closing call-to-action — ready for the full episode script.

Intro script in teleprompter

A 60-second, audio-edited intro — approved by your Audio Editor and loaded for recording.

Ethics Moment

AI voice technology can now produce audio that sounds indistinguishable from a real human host. What does that mean for podcasting — and for trust in audio media?


The Transparency Question

If a podcast uses an AI-generated voice to host an episode, should listeners be told?

Scenario A — Entertainment podcast

A pop culture recap show uses an AI voice to narrate their weekly summary. The content is accurate. The voice is clear and pleasant. No disclosure is made.

Scenario B — News podcast

A local news organization uses an AI voice to read their daily news briefing. The stories are reported by human journalists. The voice reads their scripts.

Scenario C — Sports commentary

A sports media outlet uses an AI-generated voice that sounds like a known commentator — but isn't them — to produce highlight recaps. The commentator didn't consent.

Scenario D — Your class project

You use AI to write your entire script, and then use an AI voice tool to narrate it so you don't have to record yourself. You submit it as your podcast.


Discussion Questions

Where is the line between AI assistance and AI authorship?

Using AI to research your script is clearly assistance. Using AI to write every word and narrate every sentence — with no human voice or creative decision in the final product — is closer to full authorship. Where exactly does the line move for you? Does it matter what the context is — class assignment vs. professional publication?

What are the stakes of undisclosed AI audio — and who gets hurt?

When a listener trusts a voice, they're trusting more than words — they're trusting a person's credibility, judgment, and relationship with them over time. If that voice is AI, the trust is built on something that doesn't exist. Consider: who gets hurt when that trust is broken? The listener? The journalist? The industry? All three?

In journalism, there's a long tradition of transparency about process. Anonymous sources are disclosed. Corrections are published. Why would audio be exempt from that standard?

What should AI disclosure look like in audio formats?

Written disclosure is relatively easy — you add a note. But audio disclosure is trickier. A verbal disclaimer at the top of an episode? A note in the show description? A standard industry label that streaming platforms display? Brainstorm what a realistic, honest, and listener-friendly disclosure standard would look like for audio media.


Lesson 4 Glossary

Key terms from today's session — AI research tools, audio production, and the vocabulary of podcasting.


Research & AI Tools
NotebookLM

A Google AI research tool that lets you upload your own source documents and ask questions about them. Unlike open-web AI tools, NotebookLM only answers from the documents you provide — and cites exactly where each answer came from. This source-grounding makes it significantly more reliable for professional research tasks where accuracy matters.

Source-grounded AI

An AI system that is restricted to answering from a specific set of documents you provide, rather than from its general training data. Source-grounded AI dramatically reduces hallucination risk because the model can't generate information that isn't already in your sources. The tradeoff: it can only know what you've given it.

Hallucination

When an AI model generates information that sounds accurate but is factually incorrect or entirely invented — including fake statistics, fabricated quotes, or non-existent sources. Hallucinations are especially dangerous in broadcasting and journalism because the output reads as confident and authoritative. Every fact from an open-web AI tool requires independent verification before publication or broadcast.

Narrative arc

The structural shape of a story or episode — how it begins, builds, and resolves. In podcasting, a strong narrative arc typically includes a hook (why should I keep listening?), a middle that builds tension or complexity, and an ending that either resolves the tension or leaves the listener with a compelling question. AI can help map this structure once you have your research in hand.

Audio Production
Writing for the ear

The practice of crafting audio scripts to be heard rather than read — using short sentences, conversational vocabulary, spoken-word transitions, and intentional pauses. Audio audiences can't re-read a confusing sentence or scroll back to a statistic they missed. Every scripting decision must account for the limits of the listening experience: one pass, real time, no rewind.

Double-column script

A standard professional audio script format with two columns: production notes on the left (music cues, sound effects, pauses, emphasis marks) and spoken dialogue on the right. The format separates what the listener hears from the technical instructions the producer follows. It's commonly used in radio, podcasting, and broadcast television scriptwriting.

Signposting

Verbal cues that tell listeners where they are in a podcast and what's coming next — phrases like "Coming up next…", "Here's why that matters…", or "Before we get to that, let me explain…". In print, visual design (headers, section breaks) does this job. In audio, you have to say it out loud. Missing signposts are one of the most common reasons listeners disengage from amateur podcasts.

Show notes

The written companion to a podcast episode — typically published on the podcast's website or in the app listing. Show notes include a summary of the episode, links to sources mentioned, timestamps for key moments, guest bios, and social media handles. AI is particularly useful for drafting show notes from a script or transcript, since the material already exists and just needs to be reformatted.

AI voice synthesis

Technology that generates human-sounding speech from text, often trained on recordings of real voices. Modern AI voice tools can produce audio that is nearly indistinguishable from a real person. The ethical and legal questions around these tools — consent, disclosure, voice cloning without permission — are among the most active debates in media law and professional broadcasting standards today.

Professional Practice
Scratch track

A rough, low-stakes recording made for the purpose of testing a script or timing an episode — not intended for final publication. Scratch tracks help you hear how a script actually sounds before you commit to a professional recording session. They catch problems with sentence rhythm, pacing, and word choice that aren't visible on the page.

AI disclosure (audio)

The professional and ethical practice of informing your audience when AI tools were used in producing audio content — particularly when AI was used for scripting, voice narration, or research synthesis. There is no universal standard yet for audio AI disclosure, but best practice in journalism and broadcasting is to err toward transparency: if AI meaningfully shaped what your listener hears, they deserve to know.