LinguaTune: Harmonizing Speech Barriers

Take your videos to the next level with our state-of-the-art AI platform designed to transcribe videos with near-human accuracy. Add captions or voice-over in any language of your choice effortlessly.

Live Demo

Table of Contents

1. About The Project
2. Major Technologies Used
3. Installation
4. Usage
5. Next Steps
6. License
7. Contact
8. Acknowledgments

About The Project

The goal of this project was to create a full-stack web application where users could upload or record a video, transcribe it, and provide subtitles or a voice-over in numerous languages. The project is split into three distinct parts:

1. Upload or Record: Choose your file of choice to be transcribed by our platform.

   • By clicking the Upload File button, you can upload a file from your advice.
   
   • By clicking the Record File button, your device might prompt you to enable the camera and microphone. After granting access, please reload the page if needed to see the video and audio working. Press the Start Recording button, and upon finishing the recording, you have the option to download your recording by pressing the Download Recording button or pressing the Upload Recording button, which takes you to the next step.
   

2. Select & Edit: Select a language for transcription and edit for complete accuracy. There is a transcription for Captions and Voice-Over, click the one that you'd like to edit.

   • Captions:
     1. Select the appropriate language for your transcription (01).
     2. Choose the primary and outline color for your subtitles (02).
     3. Modify the transcription in the content section.
     4. Click the Apply Captions button, wait for the subtitles to be applied, and view the video for the results.
   
   • Voice-Over:
     1. Select the appropriate language, gender and person for your transcription (01).
     2. Modify the transcription in the content section.
     3. Click the Apply Voice-Over button (currently in progress), wait for the voice-over to be applied, and view the video for the results.

3. Download: Download your upgraded video with captions or a voice-over.

   • Click the three vertical buttons at the bottom of video and select Download to download your output video.

(back to top)

Major Technologies Used

(back to top)

Installation

Please follow the instructions.

1. Clone the repository.

   git clone https://github.com/mh2rashi/LinguaTune.git

2. Install NPM packages.

   npm install

3. Get a free API Key and Bucket Name by signing up with Amazon Web Services.

4. Enter the following information in the .env file.

   AWS_ACCESS_KEY = "Enter value"
   AWS_SECRET_ACCESS_KEY = "Enter value"
   BUCKET_NAME = "Enter value"

5. Run the the development server on your local machine.

   npm run dev

(back to top)

Usage

Please access the Live Demo for this project. Wait times for subtitles and voice-over to be applied to the video are subject to its length.

(back to top)

Next Steps

• Enhance voice-over transcriptions dynamically by integrating AWS SSML Tags.
• Implement functionality to transcribe multiple voices.
• Integrate features to overlay additional components onto a video, such as GIFs or memes, etc.
• Implement features to merge videos together.
• Add more fonts for subtitles.
• Functionality to upload larger videos (Vercel only supports uploads less than 10 MB).

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Contact

Hamza Rashid

• Email : [email protected]
• LinkedIn: https://www.linkedin.com/in/mhamza-rashid/

(back to top)

Acknowledgments

I would like to thank Coding with Dawid for inspiring the project idea, and my heartfelt gratitude goes to my mentor and close friend, Fatima Taj.

(back to top)