Week 14 Speech Workshop: One True Detail, Two Takes
Part 1 — The Big Picture
This workshop is where your occasion speech meets a real listener. You choose an occasion in your own life, such as a friend's birthday, a teammate's award, a coworker's farewell, or a guest at a club meeting, and you build a toast, a tribute, or a speech of introduction on one keyword card with one true detail you saw yourself. You check it against the three criteria, occasion fit, brevity, and mood or tone match, deliver it twice for a listener, measure both takes the same way, and fix one moment between them. Along the way you use a chatbot as a rehearsal coach and then check its work, because a chatbot asked for a heartfelt toast often hands back warm lines that fit anyone, invents a rule about the perfect length, and credits a famous line to the wrong speaker.
Time budget: Plan for about 90 minutes.
Part 2 — The Task
Guiding question: When you deliver your occasion speech, does it fit the moment, stay inside its time, and match the mood, and does one true detail make your listener picture the person?
Workshop data: Your own 60- to 90-second toast, tribute, or speech of introduction: a keyword card built on one true detail, a three-criteria check, and two takes spoken aloud (student-generated)
Source: The data in this workshop is your own: a keyword card for a toast, a tribute, or a speech of introduction for an occasion you choose, built on one true detail you witnessed, a check of that speech against occasion fit, brevity, and mood or tone match, and two takes of 60 to 90 seconds measured in the tables in Part 4. Nothing is downloaded from this course, and no recording ever leaves your device. If you do not have an occasion this week, the fallback supplies an illustrative draft attributed to no one.
- Rows: 1 occasion speech per student, built on the 4 rows of the keyword card, checked on the 3 rows of the three-criteria check, delivered in 2 takes measured on the 5 rows of the measures table, and watched on the 5 rows of the listener checklist
- Columns: the keyword card has the beat, your keywords, and whether the detail is true and specific; the three-criteria check, the measures table, and the listener checklist have the row, take 1, and take 2
- Measures: the seconds from first word to the last line, a pause before the raise or the welcome, glances at the card, where your eyes went, and the one moment to fix
Part 3 — Materials & Procedure
Tools and materials
- A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach
Ways of working
- record-and-self-assess-against-a-rubric
- peer-feedback-with-a-checklist
- outline-and-oral-citation-check
Procedure
- Choose a real occasion in your life and the speech it calls for: a toast, a tribute, or a speech of introduction. Do not reuse the library retirement party; that one is the course's example. In your outline template, write one sentence naming what you are there to do, then fill in the keyword card in Part 4 with keywords only. For a toast or a tribute, use the four beats: a specific detail, what it reveals, a wish, and the raise. For a speech of introduction, use the guest, the topic, why this audience should listen, and the welcome. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: Your card has four rows of keywords, and its first row holds a detail that could only be true of this person or this guest.
- Check the card's detail: write in the third column whether you saw it yourself or checked it with someone who did. If you did not, replace it with one you did, and leave out anything the person would not want said in front of a room. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: Every row says the detail is one you witnessed or checked, and no row holds a generic line such as 'always there for everyone'.
- Do take 1 for a listener, such as a classmate, a friend, or a family member: deliver the speech extemporaneously from your card, the way you would naturally say it, and time it from the first word to the last line. You may record audio only, record video, or speak while your listener watches with no recording at all; keep any recording on your own device. Right after the take, fill in the take 1 column of the three-criteria check and ask your listener to mark the take 1 column of the listener checklist. Nerves before this are normal; a slow breath and a first line you know well both help. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: One complete take exists, both take 1 columns are filled in, and no recording has been uploaded or shared.
- Do take 2 for the same listener with one change you choose: a strategic pause before the raise or the welcome, eyes on the honoree for the wish and on the room for the raise, or a rate and tone that match the mood better. Fill in the take 2 columns, then complete the measures table for both takes, naming a moment rather than a feeling. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: Both columns of the three-criteria check, the measures table, and the listener checklist are complete, and the last row of the measures table names a moment a listener could point to.
- Rehearsal coach step: in a new chat with one approved chatbot, describe both takes and your card in words using your tables (never upload or link a recording) and ask for one specific, actionable suggestion about your detail, your wish, or your delivery. Write down its best concrete suggestion and the change you will make, in your own words, then deliver the changed moment once more. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: One suggestion is quoted, and the change you made is written in your own words.
- AI-critique step: paste the prompt in Part 6 into the same chatbot below your tables, check each answer against the checks listed there, and fill in the critique table. Or complete the equivalent route in Part 6 instead. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: The critique table quotes at least two chatbot statements, names each problem, and gives a correction with evidence, or the printed flawed response is marked up the same way.
Fallback route
When to use it: Use this route if you have no occasion in your life this week, if no listener is available, or if speaking aloud is not possible for you right now.
Do the card, check, coach, and critique steps on the illustrative farewell toast below instead of your own. Fill in the keyword card and the three-criteria check for this draft, rewrite its weak lines as keywords in your own words, use the notes on take 1 to fill in the measures table and the listener checklist, and in analysis questions 2 to 4 say what you would change in a speech of your own. You submit the same items and earn the same credit.
This route earns the same credit as the primary route.
An illustrative farewell toast for a friend moving to another city, with take notes, all attributed to no one, measured on the same rows as your own tables.
| Item | Fallback draft or take |
|---|---|
| Occasion and speech | A going-away dinner for a friend moving to another city: a toast. |
| Detail line | "You are the best, and you are always there for everyone." |
| Reveal line | "I remember the day I moved here and did not know anyone, and I went to a lot of parties that year." |
| Wish line | "Good luck with everything!" |
| Raise line | "Cheers!" |
| Speaker's notes on take 1 | Read every line from a phone, spent most of the time on the speaker's own first year in town, ran well past the 90-second limit, and said "Cheers!" with no pause, so half the table missed it. |
| Listener's checklist after take 1 | Could picture one true detail: no; stayed on the honoree: no; ended inside its time: no; feeling fit the occasion: yes; knew when to raise a glass: yes. |
| Your keyword card, three-criteria check, revised keywords, and one moment to fix |
Part 4 — The Scaffold
Build your speech on one card, with one true detail at the top, before you rehearse anything.
| Beat (for an introduction: the guest, the topic, why listen, the welcome) | Your keywords | True and specific? (I saw it, or I checked it with someone who did) |
|---|---|---|
| A specific detail | ||
| What it reveals | ||
| A wish | ||
| The raise |
Check each take against the three criteria an occasion speech is judged by.
| Criterion | Take 1: as you would naturally say it | Take 2: with the one change you chose |
|---|---|---|
| Occasion fit: the speech stays on the honoree or the guest, not on me | ||
| Brevity: seconds from first word to last line, inside the limit of 60 to 90 seconds | ||
| Mood or tone match: my words, voice, and face fit the occasion |
Measure both takes the same way so you can see what the change did.
| Measure | Take 1 | Take 2 |
|---|---|---|
| Seconds from first word to last line | ||
| A pause before the raise or the welcome (yes or no) | ||
| Times you glanced down at your card (a tally) | ||
| Where your eyes went on the wish and on the raise | ||
| The one moment to fix |
Your listener marks this checklist after each take; it shows whether the speech fit its moment.
| Listener check | Take 1 | Take 2 |
|---|---|---|
| I could picture one true detail about the person or the guest | ||
| The speech stayed on the honoree or the guest, not on the speaker | ||
| It ended inside its time | ||
| The feeling fit the occasion | ||
| I knew when to raise a glass, cheer, or welcome the guest |
Record the chatbot's answers and your corrections, or your corrections to the printed flawed response.
| What the chatbot said (quoted) | The problem it shows | Your correction and its evidence |
|---|---|---|
Part 5 — Analysis Questions
- Count the checks your listener marked yes for take 1 and for take 2 (each out of 5), show the subtraction that gives the change between the takes, and name the change in take 2 that you think caused it.
- At what moment in take 1 did your listener lose the picture or the moment to raise a glass, cheer, or welcome the guest, and what in your measures table explains it: no pause, eyes on the card, or a take that ran past its time?
- Explain why the detail on your card is specific rather than generic, using the specific-detail principle, and say which of the three criteria it helps most, with a listener-checklist mark as evidence.
- Name the delivery choice you changed in take 2, such as a pause, where your eyes went, or your rate and tone, and explain how it matches the mood of your occasion and how it would differ at a memorial or a roast.
- Choose one and answer it in 3–4 sentences. (a) A run-through for one listener is not the real occasion: what could this drill not tell you about how your speech will land in the room, and how could you find out? (b) Which beat of your card is still weakest, and what would you change before the real occasion?
Part 6 — AI-Critique Moment
Choose one equal-credit critique route. Route A: ask an approved AI tool to critique your completed work, then check its response against your own evidence. Route B is the no-AI equivalent printed below.
Approved tools: Claude, Gemini, ChatGPT, Grok, Microsoft Copilot.
Prompt to paste:
I am preparing a 60- to 90-second special-occasion speech for a public speaking class. I've pasted my keyword card, my three-criteria check, and my measures table for two takes above; I have not shared any recording. Please do six things. First, tell me what you think of my speech. Second, give me feedback on how I delivered it. Third, tell me how long the ideal toast should be, with a statistic and a source I can cite. Fourth, give me one famous quotation about community or friendship and say which speaker said it and in which speech. Fifth, rewrite my wish line so it sounds more heartfelt. Sixth, outline my speech as main points and subpoints using Roman numerals and letters.
Test the response for these likely failures:
- Chatbots often answer 'What a beautiful, heartfelt toast!' without naming your detail, a beat, or a single line that would make the room picture the honoree.
- Chatbots tell you to 'add more emotion' or 'speak with confidence' even though they never heard either take, and they name no moment.
- Asked how long a toast should be, chatbots often hand over a precise-sounding number of seconds as settled fact.
- Chatbots attach the number to 'a recent national survey' or an etiquette study with no author, title, or date you can find.
- Asked for a famous line about community, chatbots often credit a well-known line to the wrong speaker or speech, for example giving Lincoln's 'of the people, by the people, for the people' to Kennedy's inaugural address.
- Asked to make your wish more heartfelt, chatbots often return something like 'May all your dreams come true and may every day be filled with endless joy,' which swaps your concrete wish for a line that fits anyone.
- Asked to outline the speech, chatbots often write 'I. Detail. A. Story.' with no B, and lift the raise up as a separate main point.
In 3–5 sentences, quote two things the chatbot said, name the problem each one shows, and write your correction with its evidence; then name one thing the chatbot got right and the part of your card or tables it was about.
Equivalent route (no AI required)
No AI account is required for this Speech Workshop. Instead of the chatbot steps, do two things. First, for the coach step, ask your listener or another classmate for one specific suggestion about your detail, your wish, or your delivery, or reread your take 1 notes and write the one moment the listener lost the picture; then answer it with one change in your own words and try it in take 2. Second, critique this flawed response, printed here in full and attributed to no one: "What a beautiful, heartfelt toast! Add more emotion when you deliver it. Research shows the perfect toast lasts exactly 47 seconds, according to a recent national etiquette survey. As Kennedy said in his inaugural address, 'of the people, by the people, for the people.' Here is a warmer version of your wish: 'May all your dreams come true and may every day be filled with endless joy.' Here is your outline: I. Detail. A. Story. II. Cheers." Mark it up: quote each flawed sentence, name what is wrong (hollow praise, delivery feedback that names no moment, an unverified statistic, an invented source, a misattributed quotation, a voice-erasing rewrite, or an outline with a lone subpoint and a missing beat), cite the evidence from your tables, your card, or Chapter 14, and write a corrected sentence beneath it. This route assesses the same objectives (Objective 8 and Objective 5) as the chatbot steps, takes comparable effort (about 30 minutes and 200–300 words), is scored by the same scoring criteria for the same credit, and its own submission artifact is the marked-up flawed response with your coach-step question and change, posted in place of the chatbot share link and report.
Part 7 — What to Submit
- Your sentence naming the occasion and what you are there to do
- The completed keyword card with its true-and-specific column
- The completed three-criteria check for take 1 and take 2
- The completed measures table for take 1 and take 2
- The completed listener checklist
- The coach suggestion you acted on, quoted, with your change in your own words
- Written answers to the five analysis questions
- The chatbot critique report with its share link, or the equivalent route's marked-up flawed response
Deliverable:
A short Speech Workshop packet on your own occasion speech: your sentence naming the occasion and its job, the keyword card with its true-and-specific column, the three-criteria check and the measures table for two takes, the listener checklist, the coach suggestion you acted on in your own words, written answers to five analysis questions, and a critique of a chatbot's response, or, on the equivalent route, a marked-up correction of the printed flawed response. No recording is submitted. Submit in any accessible file type or as a link; a recorded response may be submitted as audio or video with a transcript, or as text. Choose a written, spoken, recorded, or visual form for your answers; every form is graded by the same scoring criteria.
Rubric
The rubric below shows how each submitted part is evaluated; bands are full, partial, or none.
| Criterion | Full | Partial | None |
|---|---|---|---|
| One true detail on a keyword card | The keyword card holds four beats of the student's own keywords in order, its detail is marked as witnessed or checked and could only be true of one person or guest, and analysis question 3 explains why the detail is specific with listener evidence. | The card is built, but one beat is missing or out of order, or the detail is generic or not marked as witnessed or checked. | No keyword card, or a card copied from a chatbot. |
| Three-criteria check | The sentence names the occasion and what the speaker is there to do, and all three criteria are checked for both takes, with the seconds recorded for brevity and a reason for each mark. | The check is partly complete, or a criterion is marked with no reason or no seconds. | No three-criteria check. |
| Two takes measured with a named moment | Both columns of the measures table are complete, each take names a moment, the listener checklist is marked for both takes, take 2 shows the chosen change, and analysis question 1 shows the subtraction. | One take is measured, a take names a feeling instead of a moment, or the change is given without the subtraction. | No take measured. |
| Coach feedback acted on in your own voice | One coach suggestion, or one listener suggestion on the equivalent route, is quoted and answered with a change in the student's own words that shows up in the revised card or in take 2. | A suggestion is quoted, but the change copies the suggestion's wording or does not appear in the revised card or take 2. | No suggestion appears, or chatbot-written lines are submitted as the student's own. |
| Critique of the chatbot or of the printed flawed response | On either route, at least two problems are quoted and corrected with evidence from the student's tables, card, or Chapter 14, every chatbot length rule, statistic, quotation, or source is marked unverified, and one correct point is acknowledged; both routes earn this band equally. | On either route, problems are named but corrected without evidence, or only one problem is caught. | No critique appears, or pasted output is submitted without any checking. |
| Reflection on the limits of the drill | The chosen reflection option is answered in 3–4 sentences that name a specific limit of the one-listener drill or the weakest beat, and a concrete way to check or fix it. | The reflection is answered but stays general, with no specific limit or fix. | No reflection appears. |
Quality Gate
- Every recording stays on your own device; none is uploaded, linked, or shared with a chatbot or anyone else, and speaking to a listener with no recording counts fully.
- Every detail about a real person is one you saw yourself or checked with someone who did, and nothing on the card would embarrass the person in front of a room.
- The keywords, the change, and the wish are your own, not a chatbot's.
- Any length rule, statistic, source, or quotation the chatbot supplies is marked unverified, and a famous line is credited only to the speaker and speech its archived transcript shows.
- Both takes are delivered to a listener and timed, and the measures table names moments rather than feelings.
- The critique quotes the chatbot or the flawed response and corrects at least two problems with evidence.
Built with The Course Maker · samples.thecoursemaker.com