How to make ‘glasses’ that transcribe text to audio for the blind

LIVE

Loading prices...

How to make ‘glasses’ that transcribe text to audio for the blind

Ana Zirojević 2025-03-20

Headgear that could help people with visual impairment perceive text by reading it out aloud in real-time isn’t a novel concept but making it by yourself at home for your loved ones might be – and an eighth-grade student has succeeded in doing just that.

Indeed, Akhil Nagori, who is a member of the 49ers STEM Leadership Institute, has created ‘glasses’ that aren’t intended for traditional seeing but are outfitted with hardware to capture text and read it aloud, sharing the entire process online in both text and video on YouTube, helping others accomplish the same.

Specifically, the setup is pretty simple for anyone with just a tad of technological inclination and includes a Raspberry Pi Zero 2W that runs off a 3.7-volt lithium-ion battery (ideally with more than 1.2 amps) and is outfitted with a classic first-party camera, like the Mini Raspberry Pi Camera Module.

The camera is mounted on a set of eyeglass frames so that it points at whatever the person wearing it might be ‘looking’ at. All it takes is a push of a button, and the camera will capture the image, passing it on to an API that does the optical character recognition, and further onto a speech synthesizer so it can be read aloud to the wearer.

Other necessary tools include jumper wires (male-to-male), two mini speakers, PLA basic filament (like Bambu Lab’s), MT3608 step-up power boost converter, soldering iron, PCB circuit board, 3D printer, and Raspbian CLI software, with the total cost of such a setup estimated at below $69.

Equipment for transcribing glasses. Source: Akhil Nagori / Instructables — *Equipment for transcribing glasses. Source:* *Akhil Nagori / Instructables*

Step 1: Text to audio glasses software

Nagori explained how he deployed the process, which included using a fast API that runs a subprocess that allows it to call the camera capture from inside the code which needs to be uploaded to the Raspberry Pi.

Update your system

To begin, you’ll need to enable SSH on the Raspberry Pi, “so you can use the terminal directly through your other computer.” Furthermore, before installing dependencies, you’ll need to update your Raspberry Pi.

bash

sudo apt update && sudo apt upgrade -y

Enable the camera

To enable the camera if using Raspberry Pi OS, open Raspberry Pi configuration:

bash

sudo raspi-config

Go to Interfacing Options → Camera → Enable.

Reboot your Raspberry Pi:

bash

sudo reboot

Install required software

Then, install the required software, including Python dependencies:

bash

pip install RPi.GPIO requests espeakng opencv-python

Test if RPi.GPIO is installed:

bash

python3 -c “import RPi.GPIO; print(‘RPi.GPIO is installed!’)”

Write the Python code

Now it’s time to write the Python code, first creating a new Python script:

bash

nano button_ocr.py

Paste the following complete script:

import RPi.GPIO as GPIO
import requests
import espeakng
import cv2
import subprocess
import time

# Define GPIO pin for the button
BUTTON_PIN = 17

# Set up GPIO
GPIO.setmode(GPIO.BCM) # Use BCM pin numbering
GPIO.setup(BUTTON_PIN, GPIO.IN, pull_up_down=GPIO.PUD_DOWN) # Internal pull-down

def capture_and_process():
“””Captures an image, processes it with OCR, and converts text to speech.”””
image_path = “captured.jpg”
# Capture image using libcamera-jpeg
subprocess.run([“libcamera-jpeg”, “-o”, image_path, “–width”, “640”, “–height”, “480”])
# Verify if image was saved
image = cv2.imread(image_path)
if image is None:
print(“❌ Failed to capture image!”)
return
print(“✅ Image captured successfully!”)

# OCR function
def ocr_space_file(filename, api_key=’helloworld’, language=’auto’, ocr_engine=2):
api_url = ‘https://api.ocr.space/parse/image’
payload = {
‘isOverlayRequired’: False,
‘apikey’: api_key,
‘language’: language,
‘OCREngine’: ocr_engine,
}
with open(filename, ‘rb’) as f:
response = requests.post(api_url, files={‘filename’: f}, data=payload)

if response.status_code == 200:
result = response.json()
if ‘ParsedResults’ in result and result[‘ParsedResults’]:
return result[‘ParsedResults’][0].get(‘ParsedText’, ”).strip()
else:
print(“⚠️ No text found in the image.”)
return “”
else:
print(f”❌ OCR Error: {response.status_code}, {response.text}”)
return “”

# Run OCR
text = ocr_space_file(image_path)

if text:
print(f”📝 Extracted Text: {text}”)
# Convert text to speech
tts = espeakng.Speaker()
tts.wpm = 100
tts.say(text.replace(“\r\n”, ” “), wait4prev=True)
else:
print(“⚠️ No text extracted from the image.”)

# Main loop to wait for button press
print(“🚀 Waiting for button press to capture an image…”)

try:
while True:
if GPIO.input(BUTTON_PIN) == GPIO.HIGH: # Button is pressed
print(“🔘 Button Pressed! Capturing image…”)
capture_and_process()
time.sleep(1) # Debounce delay
except KeyboardInterrupt:
print(“\n🛑 Program terminated.”)
GPIO.cleanup() # Clean up GPIO settings

Save the file (CTRL + X, then Y, then ENTER).

Running the program

Run the script:

python3 button_ocr.py
The program will wait for a button press.
Press the button → It captures an image.
The OCR extracts text.
The text is spoken using espeakng.

After taking these steps, you’ll be ready to run the code. Upload the main.py file and tts.py file to the Raspberry Pi, and copy the code from tts.py to the end of main.py, so they run in one execution. Now, you should have working text-to-audio glasses, but you must replace the test image in main.py with <imagename>.jpg.

As Nagori explained, “this will be used later when setting up the sound to the raspberry pi.”

Step 2: Text to audio glasses hardware

Our young programmer then uploaded the files needed to print on a 3D printer, alongside using the software for your printer to slice the uploaded .stl file.

One of the glasses’ images for the 3D printer. Source: Akhil Nagori / Instructables

Conclusion

Today’s world is more visually-impaired-friendly than before, but there is still plenty of text that isn’t translated in a form understandable to the afflicted (in braille, audio, etc.). With his project, Nagori wanted to address this problem and provide visually impaired people with access to more written text.

As he pointed out:

“We successfully developed a prototype system that uses a Raspberry Pi, a camera module, and a push-button interface to capture images, extract text using Optical Character Recognition (OCR), and read the text aloud using text-to-speech (TTS) technology.”

On top of that, he “implemented OCR using the OCR.space API and integrated espeakng for speech output,” and optimized the system to “function effectively in various lighting conditions and text formats, ensuring accessibility and ease of use.”

Nagori’s project outline. Source: Akhil Nagori / Instructables

This way, Nagori said he had demonstrated the “feasibility of a low-cost assistive device that enhances independence and daily interactions with printed text.” And it’s true – artificial intelligence (AI) glasses might be all the rage now, but solutions such as this one have the chance to help those who can’t use them yet.

Watch the demo of Nagori’s project at work:

How do you rate this article?

Subscribe to our YouTube channel for crypto market insights and educational videos.

💥The EU's finally catching up to the Crypto Race

Bitcoin might be losing to gold 💀

💥Trump Just Cancelled Europe's' Tariffs

🏆This is how you build a WINNING Crypto Portfolio

😳BitMine Just Made a $200M Bet on Mr Beast!

💥Iran's Crypto Activity Just Exploded

Subscribe View all videos

Briefly, clearly and without noise – get the most important crypto news and market insights first.

Join our Telegram TechGaged Global

Follow on Flipboard @TechGaged

Tags:

Ana Zirojević Crypto journalist and market analyst with 7+ years of experience covering digital assets, blockchain technology, and data-driven market analysis.