This is the prompt that is referred to in the video. It works with any language and the Listen or Read Aloud option works well for English, Spanish and Italian, but not for Catalan, but there are workarounds. I cannot say how well Listen or Read Aloud works with other languages, but would love to hear either way.
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.
But if you want to see if there have been any updates, use this link:
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.
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:
Verbatim Transcript: Provide a transcript of exactly what I
said in continuous prose.
Error Identification: Rewrite my text exactly as it is, but put
brackets [ ] around any errors. Do not correct them yet.
Pronunciation: Identify the top 2 issues. Use simple
descriptions (e.g., "The 'H' sounds like a breath") instead of
technical terms.
Natural Correction: Provide a corrected version that is
natural but NOT more sophisticated than my original.
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.
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.
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.
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')
Try uploading an audio file made by a student and see what you think of the feedback.
My prompt for Google's AI Studio was, "I want to build a web app where i can upload an audio file and get feedback on my speaking including my pronunciation"
I asked Gemini, "What audio and video file formats can be uploaded here to ask for feedback on pronunciation and speaking in general?"
To help you and your students use this workflow effectively, here is a breakdown of the supported formats.
Since your focus is on analyzing speech patterns and pronunciation, audio files are usually the most efficient, but video files also work well if the student wants to show their facial expressions or mouth movements.
Supported Audio Formats
These are the most common formats for voice recordings:
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
Supported Video Formats
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 "Half-CEFR Level" analysis, recordings between 1 and 3 minutes are ideal. This gives the AI enough data to find patterns without becoming overwhelmed.
Pro-Tip for your Students:
If a student is using a smartphone, I recommend the following:
iOS: Use the Voice Memos app (saved as M4A).3
Android: Use the built-in Voice Recorder (usually saved as MP3 or M4A)
Environment: Remind them to record in a quiet room. Background noise (like a TV or wind) can cause the AI to create an incorrect transcript, which will ruin the bracket [ ] error-finding step.
More details on File sizes
Here are the upload limits for audio and video files in the standard Gemini web app (gemini.google.com) and mobile app:
Video
Maximum File Size: 2 GB per file.
Length Limit:
Free Version: Up to 5 minutes total duration per prompt.
Gemini Advanced: Up to 1 hour total duration per prompt.
Audio
Maximum File Size: Generally up to 100 MB (often treated under the general file limit).
Length Limit:
Free Version: Up to 10 minutes total duration per prompt.
Gemini Advanced: Up to 3 hours total duration per prompt.
Key Notes:
You can upload up to 10 files in a single prompt.
The limits apply to the total duration in a single conversation turn (e.g., if you are on the free plan, you could upload two 2.5-minute videos, but not two 3-minute videos).
