Traditional methods of legal documentation are plagued by inefficiencies like transcription errors, delays, and in accessibility for marginalized populations. JusticeEcho, an AI-powered system, addresses these issues by integrating Whisper for accurate speech-to-text transcription and Llama for extracting structured data from unstructured audio. MongoDB’s NoSQL database ensures scalable and efficient storage of FIR records. JusticeEcho automates verbal complaint transcription, maps responses to FIR questions, and organizes data for easy retrieval. Its multilingual capabilities and intuitive design enhance accessibility and reduce procedural delays. The integration of speaker diarization enables the system to distinguish between multiple speakers in an audio recording, ensuring accurate attribution of statements in FIRs and interrogations. This prevents misidentification and enhances the reliability of recorded testimonies. Key features like emotion detection, voice stress analysis, and speaker diarization add depth to interrogation insights, improving decision-making. Additionally, the system ensures better data security and compliance with legal standards, making it a reliable tool for law enforcement. This study highlights JusticeEcho’s role in modernizing legal processes, demonstrating its scalability, efficiency, and potential for broader adoption across jurisdictions. Future enhancements such as mobile platform integration, real-time transcription, and improved diarization accuracy will further extend its impact, revolutionizing justice delivery systems worldwide.