1. Finish editing the image page.
2. Click on AI voice on the left-hand pane.
3. Choose a voice (eg, AmE vs BrE; male vs female) to preview.
4. Then click 'Generate Voice' at the bottom.
5. Then Edit as video. Adjust the length of the voice track.
6. Download the video as MP4.
7. The above can be repeated page after page.
=========
TAKEAWAY
Can add voiceover to images in Canva.
1. Prepare PPT; insert links in slides as usual.
2. Upload to Google Drive as a Google Slidedeck.
3. Go to Wayground; import from Google Drive.
4. Publish
========
In 'Preview' mode, we can see that the links are clickable.
===============================
TAKEAWAY:
- It's OK to start with PPT, which has many functions.
Earlier on, I created a poster using Gemini. The visual output is fine, but there was a spelling mistake.
Thanks to Ada Lam, who alerted me to the "EXIT TEXT IN IMAGE" function in Canva:
1.
https://www.canva.com/features/edit-text-in-image/
2. Upload problem image.
3. Grab text box in uploaded image.
3. Click 'Edit' icon:
4. Choose 'Fix Spelling'
Previously, I created an infographic on Saving the Environment, from a simple prompt, using Canva AI.
Just now, I wanted to use Canva's Code for Me, to create an interactive blank-filling task (fill in the headings for the 5 sections in the infographic).
But I was not able to upload my infographic. It referred to my prompt, and generated a general one as below: https://paulsze.net/eco-friendly-tips
Canva:
Left-hand pane > Canva AI >
Prompt box:
Create a horizontal infographic for grade 7 students titled ‘5 Things You Can Do to Save the Environment’. The infographic should include text and images. The images should help illustrate the action in question.
OUTPUTS:
4 versions:
downloaded it.
Then I went to POE, uploaded the infographic image file, and asked the chatbot to generate 6 reading comprehension questions based on the infographic.
It worked.
https://poe.com/s/2nr37yFmu77eaGXsUrNW
STEPS:
1. In Workflowy, collapse a rundown to the levels which I want to show on a mindmap.
2. Copy and paste this list into Dynalist
3. In Dynalist, copy this back to Workflowy
4. Export as a Markdown file
4. In EdrawMind, under FILE, import this Markdown file.
==
KEY TAKEAWAY
- Unlike Xmind and Mindmeister, a mind map thus created in Edrawmind can start with the top node.
最近test-drive 了幾個供實時turn-based 的voice chat AI app。背後的科技已發展得很好，是很好的外語conversation practice 的工具。Elsa Speak, Loora AI， Speak 等更可以因Learner 的需要，進行customised 的voice chat, 但要收費。
當然有些chatbot 也可以和用者進行English voice chat；暫時我試過最好的是Copilot, 就算我說得「論盡」, 它也明白我的意思；而且它反應夠快，你說完後不夠一秒，它已經回應，結果是一個很natural 的對話。除了fluency practice, Copilot voice chat還可以教你features of English pronunciation 例如stress, rhythm, intonation。
Doubao也不錯，還會把雙方的說話實時在螢幕transcribe 出來。對中小學生是很有用的功能。
|
|
WEB APP |
ANDROID APP |
|
DOUBAO |
Yes, but need to click ‘Play’ to
listen to AI conversant -
Simultaneous transcription |
Fully realtime -
Simultaneous transcription |
|
COPILOT |
(in Edge) Fully realtime -
Post-chat transcription available |
Fully realtime -
Post-chat transcription available |
I tried the Web version on my computer, as well as the desktop app.
The setting for microphone input was a bit complicated.
Anyway, from the homepage, I clicked the microphone icon in the lower right corner of the prompt box.
I then started speaking in English. When i was done, I clicked on the icon again.
My utterance would be transcribed.
Then Doubao would reply in text format.
If I want to hear it, I clicked on the loudspeaker icon below the prompt box.
===
KEY TAKEAWAYS
1. It does a good job in recognizing my utterances.
2. it prompts the conversation quite naturally.
3. But it's not real time, like Loora AI, as to hear Doubao, I have to press the button every time.
4. On the other hand, for ESL learners, it may be an asset, as they have the written dialogue to refer to.
Canva AI can also generate infographics from a text, and the outputs are quite eye-catching. On closer look, however, like the free tier of Google Gemini, the generated infographic is full of spelling mistakes!
So, NotebookLM still trumps all other AI tools as far as generating infographics is concerned.
1. I first came across the following Tense Master app created in Poe by a teacher:
https://poe.com/preview/zyuhXdEiyCboeQ3OWxTY
2. Inside each level, there are 3 Practice Formats:
4. I turned to Poe, and asked if I provided it with the share link (preview link), would it be able to write the prompt for me.
5. It asked me to provide the share link. Then it said it could not access the preview link app content. It then asked me for some details, and in particular SOME SCREEN SHOTS.
6. I simply too 4 screenshots, in sequence if one is to use the app.
7. Poe then wrote a very lengthy prompt.
8. I copied the prompt, and pasted it into App Creator.
9. It worked, though it took quite a long time for App Creator to finish the task.
OUTPUT:
=========================================
TAKEAWAYS
1. Though I have yet to check out the content, the resulting app looks good.
2. This experience shows that if I come across another elaborate canvas app, but do not wish to spend a lot of time figuring out the prompt, I can (a) describe my needs, and (b) attach some screenshots of the original app, and ask a chatbot to write the prompt for me. THIS WILL SAVE A LOT OF TIME.
Just found another excellent example for my upcoming Language Awareness course.
The conventional textbook/teacher explanation would be:
"- We use an adverb of manner to describe how the action represented by the verb phrase happens.
- We form an adverb of manner by adding '-ly' to the adjective; hence 'wrong (adj.) > wrongly (adv,).
Under a language awareness approach, a possible lesson sequence (for post-intermediate learners) would be:
============
Step 1: Show Ss the example below ( "I used NotebookLM wrong"); ask Ss if they notice anything 'unusual' about the sentence.
Step 2: Show the following 2 sentences. Invite Ss to judge which one(s) is/are acceptable: (a) He did it wrongly; (b) He did it wrong.
Step 3: Present other example sentences (e.g., He ran fast; She arrived at school late; They worked hard), and ask learners to decide whether the last word in each sentence is an adverb. Sum up by guiding learners to see that not all adverbs end in -ly. (Introduce the term 'flat adverb' if necessary.)
Step 4: Invite learners to come up with similar example sentences. If necessary, provide them with such adverbs (e.g., right; high; far)
Step 5: With advanced learners, challenge them by asking them to look for the subtle difference in meaning between (a) He did it wrong, and (b) He did it wrongly.
Step 6: Finish by inviting Ss to share their thoughts on the slogan used by Cityplaza: 'LIVE HAPPY.'
=================
In fact, with the advent of AI, students can learn a lot about language matters from chatbots. It's really time we stopped relying totally on abstract, unreliable, 'rules' in our grammar teaching.
Original lesson plan file: lesson flow for a UDL-aligned KS2-3 reading lesson.pdf
(A lesson plan created by GPT5.2, for Grade 5, on the a passage 'Simple Machines' (150 words), for grade 5)
+++++++++++
At app.Classwork.com, I:
1. uploaded my original passage PDF;
2. on the dashboard, chose 'text box';
3. moved on the text box to cover each word I wanted to cover;
4. saved; and
5 got the Assign Share link: https://app.classwork.com/fill/4ba4dc3a-1250-4daa-9fa9-daf4a52b5a1f
++++++++++++
TAKEAWAY
1. Quite easy to create a worksheet.
2. Ss can know the score immediately once they 'submit'.
3. Liveworksheets.com cannot cover a word and turn it into a blank.
