A long prompt to get feedback on your speaking from audio files uploaded to Gemini

Below is the prompt that I have been experimenting with recently for students to use to get feedback on their speaking with when uploading a short audio file to Gemini and here is a 20-minute video showing it at work in three languages: Spanish, Italian and Catalan:

Language Coach Prompt

I am a language learner. I will upload audio files for you to analyse. Your goal is to be a helpful coach.

Core Communication Rules (Apply to EVERYTHING you say):

• Match My Level: You must use vocabulary and sentence structures that match the CEFR level of the audio I upload. If the audio is A2, your explanations and instructions must be A2.
• Language: If the audio is in English, use British English spelling and vocabulary at all times. If the audio is in another language, all responses should be in that language at the level of the recording from the very beginning
• No Jargon: Do not use academic or formal words (e.g., avoid "transitioned", "lexical", or "syntax"). Use simple, natural words a native speaker uses in daily life.
• Scannability: Use bullet points for clarity. Never use tables. Avoid long walls of text.
• Wait for Audio: Do not give any feedback or assessments until I upload a file and you know which language I speak and have heard my level.

The Process: When I upload a file, first ask if I want "Quick Feedback" or the "7-Step Sequence." If I choose the sequence, ask which step I want first. After every step, list the remaining options as briefly as possible.

The 7 numbered Steps:

1. Verbatim Transcript: Provide a transcript of exactly what I said in continuous prose.
2. Error Identification: Rewrite my text exactly as it is, but put brackets [ ] around any errors. Do not correct them yet.
3. Pronunciation: Identify the top 2 issues. Use simple descriptions (e.g., "The 'H' sounds like a breath") instead of technical terms.
4. Natural Correction: Provide a corrected version that is natural but NOT more sophisticated than my original.
5. Colloquial Version: Create a version that is slightly more casual/conversational. It should be less than half a CEFR level higher than my original. List 3 changes and explain them simply.
6. Advanced Version (Level +0.5): Create a version that is roughly half a CEFR level higher than my original. Focus on natural spoken language. List 3 specific changes and explain why they are a better "bridge" to the next level.
7. More Advanced Version (Level +1.0): Create a version of spoken language that is roughly half a CEFR level higher than the previous "Advanced" version (one full level above my original). List 3 changes and explain how they help me reach this higher level.

Feel free to copy and paste this prompt into a free account with Gemini or experiment with your own variations. All you will need then are some audio files in one of these formats:

• MP3 (The standard format for most phones and voice recorders)
• WAV (High quality, but larger file sizes)¹
• AAC / M4A (Common for iPhone "Voice Memos")²
• OGG
• FLAC

If a student records themselves on camera, these formats are supported:

• MP4 (The most common format for smartphones)
• MOV (Standard for Apple devices)
• AVI
• WMV
• WebM

Key Technical Limits

File Size: Generally, files should be under 20MB for the best performance. If a video is too large, it is often better to convert it to audio (MP3) before uploading.

Duration: For a detailed analysis, recordings between 1 and 3 minutes are ideal. This gives the AI enough data to find patterns without becoming overwhelmed.

Can you adapt this to be in Catalan and for the CATALAN language?

One of the wonderful things about Google's AI Studio apps is that anyone you share them with can adapt them very easily.

I asked, "Can you adapt this to be in Catalan and for the CATALAN language?"

In less than a minute it had produced this:
Here's a link to the SpeakSmart AI Català app

I allowed these two

I then uploaded an mp3 file, but SpeakSmart AI also accepts:

opus, oga, flac, ra, webm, weba, wav, ogg, m4a, mp3, mid, amr, aiff, wma, au, aac

SpeakSmart took a minute or two to produce this feedback:

3 anècdotes 28/01/2016

72

General

75

Pronunciació

78

Claredat

65

Ritme

Transcripció

"Una vegada, fa molts anys, vaig anar al teatre... crec que era al Mercat de les Flors. No? Hi havia un teatre... una miqueta... alternatiu. No clàssic, però clàssic com els teatres del centre de Barcelona. I hi havia una obra de Nick Hornby que tractava del futbol, dels 'hooligans'. I a la mitja part de l'obra vam anar, jo i la companya, al bar i Joan Puigcorbé, l'actor... estava allà al bar. I només ell i nosaltres dos al principi, i hem parlat amb ell, que ell estava de públic, no d'actor. Molt agradable. Una altra vegada, la meva dona... anàvem passejant per la costa de Tarragona, a prop de la Punta de la Móra. Vam anar passejant, vorejant el mar, i hi havia un tros molt difícil, un caminet molt estret... unes roques... i ens hem trobat una tanca. I per salvar-nos hem saltat la tanca i ha arribat un... de seguretat... de la Punta de la Móra, que és un càmping privat, no? I ens ha dit: 'Aquí no pots creuar la tanca, home! És que és perillós aquí'. I al final ens han deixat passar. Una vegada també, fa molts anys, en el ferri d'Anglaterra a França, jo i un amic... més de 50 anys... era un ferri de nit. I hem decidit pujar amunt a veure el mar de nit, la lluna i tot això, que és molt bonic. I també l'única persona allà, a part de nosaltres, era un cantant famós que estava allà gaudint de la vista."

✨Punts forts

• ✓Bon ús dels temps verbals en passat (vaig anar, anàvem, hi havia) per construir la narrativa.
• ✓Vocabulari ric i adequat al context (vorejant, tanca, alternatiu, públic).
• ✓Capacitat d'autocorrecció i de donar detalls descriptius per enriquir la història.

💡Consells generals

Tens una bona capacitat narrativa i un vocabulari extens. El teu principal punt de millora és la fluïdesa; intentes buscar la paraula exacta, cosa que provoca pauses freqüents i l'ús de 'ehm'. Intenta estructurar la frase mentalment abans de començar per millorar el ritme. També, vigila la coherència dels temps verbals quan expliques històries (intenta no barrejar el 'vam fer' amb el 'hem fet' si l'acció és llunyana).

Millores específiques

Paraula/Frase	Problema	Suggeriment
la meva dona... anàvem	Concordança de subjecte	La meva dona i jo anàvem / Amb la meva dona anàvem
ens hem trobat / hem saltat	Barreja de temps verbals (Perfet vs Perifràstic en narració)	ens vam trobar / vam saltar (per mantenir la coherència amb 'vam anar')
un de seguretat	Precisió lèxica	un vigilant de seguretat
Joan Puig Corbé	Nom propi (probable confusió)	Juanjo Puigcorbé

© 2024 SpeakSmart AI - Català. Creat amb Google Gemini 3.

   

 

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.

This is the second thing I suggested to other teachers at the Language Show - Show and Tell

Using NotebookLM with "Dolphins save Swimmers" by Lidia G

This is one of the things I suggested to other teachers at the Language Show - Show and Tell

Bargain Sweater Turboscribe ai and ChatGPT

Further experiments with students recording themselves, getting a transcript and getting AI to tidy it up

I want to be able to suggest a series of steps language learners can follow using just their mobile phones to get feedback on their speaking. 

Over the last four days I have been practising the steps using our granddaugher as a pre-intermediate learner of English. The procedure involved combining two of my obsessions: getting students to do extensive reading and getting them to record themselves retelling stories. 

1. I asked her to read an Oxford Bookworm Starter level reader on the Oxford Reading Club app
2. She then told me the story in her own words without recording herself
3. She then recordered herself retelling the story using 'Voice Capture' on Microsoft 365
4. Voice Capture generates a transcript automatically. I Shared the recording (and transcript) as a Word document
5. I copied and pasted the transcript into three AI webpages and asked for the transcript to be tidied up
6. I copied these 'improved' transcripts back into the Word document where with 'Read Aloud' she could listen to the suggested changes.
7. She selected which of the improved transcripts was the best and I copied and pasted it into WhasApp for her.
8. I then used WhatsApp to record 'Read Aloud' and add that so she could listen to it again.

Here's a short video I made and posted on YouTube:

My original idea was that this sequence would be followed by a repetition of the task of retelling the stories. However, I didn't use this idea, partly because my granddaugher's original recordings were about 9 minutes long, which is much much longer than my students' typical recordings of two to three minutes, but also because I was beginning to think that the exposure to up to five versions of her own story might be of sufficient benefit. I'm still open to suggestions on this.

Here are two of the AI suggestions - (with the Microsoft Edge browser you can select and right-click and choose 'Read Aloud' to listen to these versions)

ChatGPT suggested:

"The Mystery of Manor Hall" is about two brothers visiting their uncle's dark and mysterious house, which is very big. The brothers visit their uncle's house while their mother is buying a new house and getting everything in order. When they arrive at their uncle's house, he allows them to explore and enter all the places, except for the music room, which makes them curious.

During supper, the uncle points out the new moon and tells them they can't leave their room that night. Later, the sister wakes up and hears a strange sound. The brother listens and convinces his sister to go to the music room. They think they hear their uncle singing, but upon entering, they see a picture of a pirate. The pirate notices them, and they become frightened and attempt to leave the room, but the pirate prevents them from doing so.

The pirate explains his story to the brothers. He used to have a magic picture that allowed him to go sailing with his ship every new moon, but now the house is far from the sea, so he's unable to do so. Meanwhile, the uncle arrives and reveals his story. He had bought the house from an old man who warned him not to enter the music room due to a ghostly presence. The uncle had been afraid and avoided the room ever since.

Eventually, the two brothers move with their mom to the new house, which is located near the sea and took the magic picture. Every new moon, the pirate can now sail and sing quietly. And this is the end of the story.

Bing suggested:

The story is about two brothers who go to their uncle's house. The uncle's house is very dark, mysterious, and big. The brothers go to their uncle's house because their mother is buying a new house and needs to get everything in order. When the brothers arrive at their uncle's house, their uncle tells them that they can look for things and enter all the places in the house, except for the music room.

The brothers are confused because they can't go to the music room. Their curiosity gets the better of them and they try to enter the music room, but their uncle sees them. In the evening, while they are having supper, their uncle tells them to look at the new moon and that they can't leave their room that night.

In the middle of the night, the sister wakes up and tells her brother that she hears a strange sound. The brother listens and they both go outside their room. They don't want to, but they finally go to the music room. They think it's their uncle singing, but when they enter, they don't see anyone. When they turn on the lights, they see a picture of a pirate.

The pirate sees them and comes out of the picture. The brothers are very afraid and want to leave the room, but they can't because the pirate won't let them. Finally, the pirate explains his story to the brothers. He tells them that one day an old woman painted a picture of his ship and said it was a magic picture because every new moon he can come out of the picture and sail with his ship.

He could only do this if the picture was near the sea, but now the house isn't near the sea and he is sad because he can't sail. Then their uncle arrives and explains his story. He bought the house from an old man who told him not to enter the music room because 

How to use AI to get feedback on your speaking and learn from it

•  Record yourself doing a speaking task

• Use Word to get a transcript and add it to Column 1

• Manually correct the transcript as far as you can and add it to Column 2 (use tracking)

• Ask Bing AI Chat to "tidy up" your transcript and copy it to column 3

• Mark the mistakes in column 2 in red and the corrections in column 3 in green

• Copy what you have learnt into your notes (see below)

• Select the transcript in column 3, right-click on it and click on Read Aloud
• Practise reading this transcript aloud
• Try recording the story again without reading the transcripts
• Check you have got the five things to learn right this time

5 things to learn

• wait for someone

• Jenny is waiting for Rob in Central Park.

• have something to share/do/wear

• Both have good news to share.

• tell someone to do something
• Rob tells her to speak first.
• she/he doesn't need ...
• She doesn't need to move to London
• she tells her ... third person -s
• Jenny tells Barbara to delete her email.