A powerful C++ application that captures live audio (like Chrome Live Captions) and converts it to text in real time β ideal for accessibility, meeting notes, interviews, or AI-assisted conversations.
Translate speech instantly, save transcripts automatically, and connect with GPT-based tools for smart analysis.
π AI/ML Engineer | Software Developer | .NET / C++ / Java Specialist
I'm passionate about creating scalable, intelligent, and accessible applications that bridge technology and human needs.
Currently working on AI-driven accessibility tools and real-time applications using modern frameworks.
- πΌ Software Engineer experienced in C++, C#, Java, and .NET Framework
- π€ Enthusiastic about AI/ML applications, automation, and assistive technology
- π‘ Focused on transforming ideas into high-impact software solutions
- Ensure Live Captions are enabled in Chrome.
- Run the C++ app to capture captions from media in Chrome, including GPT-powered interviews.
- The app automatically processes the captions and displays them as text in real-time.
- Optionally, save the text or copy it for further use!
- Job Interviews: Capture real-time captions from AI-assisted interviews with GPT or other platforms, making it easier to review and follow up on questions.
- Content Creators: Quickly save captions from online videos for script writing or analysis.
- Accessibility: Enhance accessibility by converting captions into text for users who need text-based content.
- Language Learners: Capture and review spoken content to aid in language transcription and learning.
- Developers & Researchers: Use captured text for speech-to-text projects or natural language processing (NLP) experiments.
- C++: Core language used for high-performance real-time text capture.
- No OCR: This tool extracts text directly from Chromeβs Live Caption pop-up window without using OCR, making it lightweight, fast, and fully local with no network traffic required.
This project is licensed under the MIT License.
C++, Live-Caption, Text-Capture, Job-Interviews, GPT, Speech-to-Text, Chrome-API, Accessibility, Multi-Language-Support, Real-Time, Audio-To-Text, Voice-To-Text, Speech-Recognition, Audio-To-Text, Transcription, caption-generator
- π Launch 3 open-source AI or .NET projects
- π¬ Share tech insights via blog posts
- π― Contribute to accessibility-focused open-source tools
βοΈ If you find my work useful, please consider giving a star!
Β© 2025 Jeremy. All rights reserved.
