Using Clipchamp to prepare the video of me rehearsing for a webinar for TESOL Simple Education in Vietnam

Layout of video

I did the webinar more than a month ago and on and off in the last month I've been trying to edit the video that I made using Zoom to prepare for it. The video had to be in two parts because my free Zoom account limited me to 45 minutes.

There were a number of problems that I had to solve:

• I must have coughed at least twenty times
• Some of the audio I played was too quiet
• I needed to add some text to suggest viewers pause the video to do the different tasks, or to explain things I hadn't remembered to explain.
• I wanted to add subtitles in English, Vietnamese, Kazakh and other languages

I'm still not sure whether to post just one long video or to break the video up into four or five linked videos. Maybe I''ll do both but for the moment it's just one with chapters

Coughs

I have always used Microsofts Clipchamp to edit videos and I discovered that there are two ways to remove the coughs: you mark with the scissors just before and after the cough. Then you can either turn off the sound in that very short segment of the video or delete it. Deleting it was my first choice as it shortened a very long video.

Too quiet audio

My first approach was to mark the segment where the audio was playing, turn off the sound and add an additional audio track in its place. I learnt through trial and error that another way to solve the problem is to mark the segment and then cick on 'Audio' on the right ansd pt the volume up much higher for that segment.

Adding a text box

I found that there was an area on the right of the screen under the next slide and my face, which was always empty and where it would be best to add a text box. I had to make my instructions or comments very brief.

Subtitles in Vietnamese and Kazakh

I exported the .srt file with the subtitles in English from Clipchamp and uploaded them to YouTube. I then asked YouTube to provide subtitles in these two languages as well as in the languages in which I could check that the translations were correct: Catalan, Spanish, French and Italian.

Here, finally is the 75-minute long video with the following chapters:

00:00 Intro + using Turboscribe.ai and ChatGPT to get feedback on speaking

08:45 Demonstration of the nine-step prompt to get feedback on speaking

28:54 Now you do it - a hands-on task as if a student wanting feedback on their speaking
58:41 Suggestions for communicative speaking tasks for students to do in and out of class

1:11:47 Outro + websites that help your pronunciation, Facebook groups on edtech

 

ChatGPT interviewing me about the Spanish Couple on the Titanic

Daniel Martin suggested on Facebook that with the right prompt ChatGPT could interveiw anyone using voice. From reading to speaking practice I adapted his prompt to make it easier for students to use it with any text they wanted.

Here is the text that I used for this experiment:
https://www.bulldogz.org/post/titanic-tales-a-single-spanish-victim

Here is the ChatGPT conversation, which is only a text chat:
https://chatgpt.com/share/67b0f234-9a28-800b-9000-c3f06260a3ff

And here is the recording I made of the interview:
https://www.rev.com/app/transcript/NjdhZmEyZDg1YWFjZGMzOTA2YjQ1ZWY1N3dLMk9scE11b2NY/o/VEMwMTk3MzQ5MDA2

You can watch a video about it here:

I would love to see a similar video made by a student.

Turboscribe versus Rev - the two best and most generous transcription tools

I asked NotebookLM to do the heavy lifting of comparing three transcripts saved from Turboscribe (x1) and Rev (x2)

This is an edited version of how it replied to my question:

“I am interested in any differences between the three transcripts particularly regarding the use of interjections and the use of phrases like 'like', 'you know', 'um' etc”

Differences appear in the transcripts regarding interjections and phrases such as "like," "you know," and "um." The transcript generated by TurboScribe.ai, includes these kinds of interjections and phrases more frequently compared to the two transcripts generated by Rev.com

For example, the TurboScribe transcript includes the parts in bold that are missing from the Rev transcripts:

·         "[M] Right. It's like we're on the edge of this revolution, you know, and how we learn and practise speaking. Like it's a total paradigm shift"

·         "[M] Exactly. And they went step by step, you know, first analyse the speech, then identify errors"

·         "[M] Exactly. So you got to clean up the transcript a bit. And then that's when the fun starts. Use ChatGPT to actually like analyse your speech and give you feedback"

·         "[M] They encourage teachers to, like, play with it, change it, adapt it, you know, and even share their own versions with other teachers"

These examples show the more conversational style captured by TurboScribe, including interjections ("wow") and fillers ("like", "you know"). The two transcripts captured by Rev appear to have had some of these conversational elements removed or edited out, presenting a cleaner version of the dialogue.

On the other hand, below is a comparison of how Rev.com with the verbatim option selected and Turboscribe, which has no such option, handles transcribing. It is very revealing:

Rev.com:

Rev heard ‘boat’ and ‘things’ and as it had been asked to create a verbatim transcript it didn’t examine how likely this sequence of words was.

Turboscribe.ai:

Turboscribe, on the other hand, correctly interpreted the learner’s intention because ‘bought’ and ‘thinks’ are more likely in the context. But this desire to predict what is more likely led it to also correct ‘womans’ to ‘women’, ‘say’ to ‘said’ and ‘are’ to ‘was’ and to insert ‘can’ into the phrase ‘you can guess’

Both Turboscribe and Rev interpreted what I heard as ‘ask her’ as ‘asked her’, but I imagine that is because the /t/ is hard to produce and often omitted by native speakers. Why ‘that’ was omitted by Turboscribe in the phrase ‘said no’ must also be down to frequency. About 161,000,000 results without ‘that’ v. About 26,900,000 results with ‘that’ according to Bing. 

There are other important differences between free accounts using Turboscribe.ai and Rev.com:

The most important advantage of Turboscribe is that it can be used from the age of 13 with parents’ permission. The other factor to bear in mind is that Rev.com only works in English on a free account at the moment. The transcripts are automatically synchronised while listening on Rev.com, whereas with Turboscribe.ai the user needs to move the page up to follow them.

But the key reason for not being able to recommend Rev.com on a mobile device is that it is: 

No longer possible to edit or download transcripts using a mobile device

When using a PC, this is not a problem.

Support on Rev.com is excellent and I haven’t needed to contact support on Turboscribe.ai

An experiment with a 5-step prompt with 5 types of GenAI

I decided that it must be possible to include all the prompts for a routine sequence of prompts in one rather long prompt.

I wanted to get:

1. A student transcript with the errors marked so they could try to see their errors
2. A corrected version of the transcript
3. An improved version at the students level (A2, in this case)
4. An improved version at the next level (B1, in this case)
5. An improved version at two levels up (B2, in this case)

The secret was to include the five steps in the prompt but to instruct GenAI to wait for the prompt “Next” before moving on to the next step.

I then took a short recording made by a very good A2 student and used Rev.com to get the transcript. The idea is that the student has to copy the long prompt from a WhatsApp group, for example, and paste it into the chosen GenAI and then copy the transcript from Turboscribe.ai or Rev.com  and paste it into the same GenAI.

I did this with these 5 types of GenAI:

1. ChatGPT
2. Gemini
3. Claude
4. Copilot
5. Deepseek

I then copied the output from each GenAI for each step and pasted it into Pearson’s GSE Text Analyzer ( https://www.english.com/gse/teacher-toolkit/user/textanalyzer ), which gave me GSE and CEFR levels for all 25 versions of the transcript.

Apart from looking carefully at the English used in each version to try to understand what language had determined the levels given for them all, I also made an Excel spreadsheet with the two sets of levels. With these I was able to produce two graphs. The first one shows what happened with each type of GenAI:

At first glance Claude was the best at producing increasingly sophisticated versions of the student’s transcript, although they were always half a CEFR level too high. Mark you, the original transcript was already half a level higher as she was a very good student.

Equally obvious is the fact that Copilot was useless!

ChatGPT, Gemini and Deepseek failed to produce increasingly sophisticated versions across the four levels, so they didn’t do what I had intended.

In fact, as can be seen in this second chart, the whole idea didn’t work on average:

Once again, this may be as a result of the student’s original transcript being higher than expected (A2+ rather than A2). Maybe the lesson to be learnt from this is that instead of using fixed levels for each step up, the different GenAIs may be able to produce new version of the transcript one level higher on the CEFR scale. This would have the added advantage that the same long prompt could be useful for all students in a class and across all courses.

Here is the original version of the long prompt derived with help from Turboscribe and ChatGPT’s advice. (I hope the concept of including steps and a trigger word will be useful):

“You will be provided a transcript as well as instructions about what to do with that transcript. Unless otherwise specified, your response should be in the same language as the transcript.[1] Here are your instructions, which you must follow:

Instructions:

1. I will provide a transcript. For each step, you should follow the instructions carefully.
2. For each task, do not include timestamps unless specifically requested.
3. After each step, wait for me to say "next" before proceeding. 

Steps:

1. Mark the errors in the transcript in bold, but do not correct them.
2. Correct the errors, marking the changes in bold and leaving the original errors in brackets.
3. Improve the transcript for A2 level students, marking improvements in bold.
4. Improve the transcript to a B1 level, marking changes in bold.
5. Finally, enhance the transcript to a B2 level, marking improvements in bold. 

[Sample transcript of an A2 student’s recording:]

The history start in the summer of 2011. Anna went on holiday with some friends on island. The photo was taken on hill. Hill is a little mountain and called Ana. The photo is important for her because the stone is a mysterious for her. And she put your hands around it, the stone, and, and she was sleeping. And this photo there are in other places because in your mobile phone, computer, et cetera.”

---

[1] These two sentences came from Turboscribe’s Custom prompt

Transcript of spoken conversation with Copilot fed into Claude to get a podcast script to use in Wondercraft to produce a podcast

This is really part 2 of a post about a wonderful conversation I had with Copilot using voice. You can read part 1, which ended with me getting a podcast produced by Google's NotebookLM, here.

I wanted to experiment as well with Wondercraft, which offers various ways to create a podcast. One way is to provide it with a script and you can then choose from different voices and add music.

I thought Claude would be a good way to get a script for a podcast based on my conversation with Copilot and that proved to be true.  I uploaded a Word doc of my conversation and said, "Can you make this into a podcast?"The script it produced was for one speaker and it suggested when to have pauses and when to insert music at the beginning and end.

I gave the script to Wondercraft and chose a woman's voice, Abby's, for the podcast and some music for the intro and outro.  I exported the .wav file and uploaded it to Rev.com to get a transcript that would be synchronised with the recording. You can see the results here as I made a screen recording of it playing on my iPad (4 minutes):

Here is the screen recording of the podcast produced by NotebookLM (9 minutes):

While both podcasts give a good account of my conversation with Copilot about a presentation I'm planning to give, my real interest is in how students might benefit from creating such podcasts based on their recorded speaking or their writing.

How to use Rev, ChatGPT, NotebookLM to help students improve their English

I've made a 30-minute video showing how students can record themselves using Rev.com, study a transcript of their recording and ask ChatGPT to help then identify errors, see what they could have said and how they should be able to express the same thing at the end of the course or next year.

A new idea I played with is to upload a series of separate prompts for ChatGPT to a class WhatsApp group so students can simply copy each of them in turn and paste them in instead of having to type them out.

The video was made using an iPad and has been heavily edited.

Rev.com is great as it gives everyone 300 minutes a month on a free account, but at present it only works for English and for people over 18. Turboscribe.ai, on the other hand, works in more than one hundred languages and can be used by people of 13-18 with parental permission as well as for over-18s.