Luggage for Children Turboscribe & ChatGPT - how to get corrections and suggestions for improvments

Breaking News!

Students can now record themselves using Turboscribe.ai

See an example showing how the transcript from Turboscribe can be pasted into ChatGPT to get corrections & an improved version at B1

Luggage for Children Turboscribe & ChatGPT

Transcript correction and enhancement by Gemini, ChatGPT, Copilot or Claude

https://g.co/gemini/share/16c0248c7a9f Transcript correction by #Gemini can be just as useful as that provided by #ChatGPT or #Copilot or #Claude

Try this prompt with them all:

Can you correct this transcript marking the errors and the corrections in some way? One evening in October, Hannah was at work. She was meeting Jamie at 5.30. She looks her watch and it was 5.20. It was raining and she was in a hurry because she has 10 minutes to meet Jamie. She was driving along the high street and she was driving very fast. Suddenly a man crossed the road and Hannah didn't see him.

Check to see if Read Aloud works on them all as it is very useful for #EFL #MFL #ESL students. 

Then use this prompt:

How could an ... level student express this better? try with A2, B1, or B2

The transcript was produced by #Turboscribe

But the innovative thing is that Turboscribe now offers a microphone option, so students can record themselves live three times a day for up to 30 minutes each time with a free account. 

Turboscribe now allows live recording!

 

Breaking news!

It may be difficult to see but turboscribe.ai is now more useful than ever as there is now a microphone so students can record themselves 3 times a day for up to 30 minutes!

The transcripts are very accurate and students can listen while following the transcript to notice automatic corrections that have been made.

Editing the transcripts to correct obvious mistranscriptions usually caused by pronunciation problems is possible, although a bit fiddly. 

(Corrected) transcripts can be exported in various formats, in which it may be easier to make corrections.

These can then be pasted into ChatGPT, for example, with prompts asking for corrections or a more coherent version at A2  B1 B2 etc

Spacebar.fm offers 200 minutes of recording, transcription, summarization, and illustration

I discover new Speech to text  platforms every week. https://spacebar.fm/app offers all this and a limited number of AI interactions.

Spacebar.fm Overview

Spacebar.fm is a versatile speech-to-text platform offering 200 minutes of free recording and transcription services, alongside a limited number of AI interactions. The service can be accessed via web browsers on computers, Android and iOS platforms with a mobile app on iOS platforms.

Features and Capabilities

1.    Transcription and Editing:

• Recording: Users can record audio and receive transcriptions.
• Summarization: Spacebar.fm provides summaries of the recorded content.
• Illustrations: The platform suggests possible illustrations for stories.

2.    Analysis and Statistics:

• Analyses speech, providing statistics such as word count, speaking speed (words per minute), and other conversational metrics.

3.    Interactivity:

• Users can request:
1. Corrected versions of transcripts.
2. AI-powered enhancements, including generating more coherent versions of text for language learners.
• The app also offers sharing options, including QR codes.

4.    Device and Platform Compatibility:

• Web (PC): Features like recording recovery, speed adjustment, editing, and copying of transcripts.
• Android: Similar functionality to the PC version, with error correction and transcript playback.
• iOS: While it doesn’t allow editing of transcripts directly, it supports copying and requesting AI-generated corrections.

5.    Usage Tracking:

• Tracks the minutes used even without signing in.

Practical Application and User Experience

Logging in on Browser Experience:

1. Imposes a 10-minute limit per recording session.
2. Allows correction of transcription and noticing automatic corrections during playback.
3. Allows limited access to AI using spacebar.fm
4. Suitable for language learners with tools to make text more coherent.
5. Enables copying and pasting of transcripts to other platforms like Padlet and GenAI.
6. Offers sharing with other users via QR codes and other methods.
7. Users can save and download audio files.
8. Users can listen to the transcript read aloud if using Edge browser.
9. Keeps recording , transcripts and summaries (Only if you log in)

Browser experience without logging in:

• 1 – 8 of when logging in
• Maintains usage tracking without requiring an account so if you finally log in it recovers your recordings, transcriptions, etc.

iOS app Experience:

• Requires iOS version 13.4 or higher.
• Extends the time limit to 90 minutes
• Doesn’t allow correction of transcription and noticing automatic corrections during playback.
• Allows more access to AI using spacebar.fm
• Suitable for language learners with tools to make text more coherent.
• Enables copying and pasting of transcripts to other platforms like Padlet and GenAI.
• Offers sharing options via QR codes and other methods.
• Users can save and download audio files.
• Keeps recording , transcripts and summaries

Age Requirements

Users under the age of majority must have parental or guardian consent to use the service. Parents or guardians are responsible for their children's activities on the platform. But spacebar.fm can also be used in a browser without logging in.

Conclusion

Spacebar.fm is a robust tool for speech-to-text needs, offering various functionalities across multiple devices. Whether for personal use, educational purposes, or language learning, it provides a comprehensive suite of tools for recording, transcribing, editing, and enhancing transcribed content.

(This is a heavily edited version of ChatGPT's attempts to make sense of my notes.)

Asking ChatGPT to use strikethrough to mark errors

 Can you correct the errors and mark the corrections in bold and show the mistakes before the corrections marked with strikethrough ? In ChatGPT

Why didn't I think of asking it to use strikethrough before?

Does it work with Copilot, Gemini and Claude, too?

Problem: Speech to text apps are too good and correct lots of mistakes that learners would do well to notice

 

Solution: Students should listen to themselves while following the transcript to notice the corrections

Most speech to text apps or webpages correct many of the errors students make. So, I suggest students should listen to themselves while following the transcript to notice the corrections, before copying and pasting it into their favourite GenAI and asking for corrections. At the same time, they should correct any mistranscriptions like writing 'hungry' when the student meant to say 'angry'.

I like ChatGPT or Copilot as with either of them students can ask for them to display the original and the corrected versions in two columns of a table marking the errors and the corrections in bold. If students want to listen to it, they need to get it to display just the corrected version. If they do this using the microphone/headset they can hear it as it appears, or they can wait and touch the speaker icon.

If learners use their voice to ask for a more coherent version suitable for a learner at level B1 on the CEFR, for example, they can read and listen to it at the same time All this will help to make your students' repetition of the speaking task even better than it would be after simply doing the same thing again.

Here are three demonstrations of this technique using Soundtype.ai notta.ai & turboscribe.ai

Watch and participate in my workshop at #iELT24 on how students can get instant feedback on their speaking in and out of class.

Try out the ideas and add your evaluations of the apps that I suggest below.

•https://soundtype.ai/en

•https://www.notta.ai/en 

#Copilot and #ChatGPT