Company: Speechlabs AI

Role: Software Architect

Product: https://www.speechlab.ai/

Project Objectives: AI-Powered Audio and Video Localization Platform

Developed a cutting-edge service that leverages proprietary AI to automate the process of video and audio localization. The platform delivers transcription, translated text, and synthetic dubbing for audio and video content, enabling speech-to-speech translation for dubbing professionally produced media.

Technologies and Tools:

Key Accomplishments:

  1. Architected the system based on Amazon Web Services (AWS) and played a crucial role in designing the overall system architecture.
  2. Developed core components of the API to access large language models, enabling seamless integration of advanced AI capabilities into the platform.
  3. Designed and documented the API layer and structure using Swagger, providing clear and comprehensive documentation for developers.
  4. Implemented a secure authentication and authorization mechanism using AWS Cognito and Node.js, ensuring user privacy and data protection.