A powerful AI Agent Demo playground that combines the intelligence of AI agents LLM with real-time speech-to-speech models integration. Build sophisticated voice-enabled applications for customer service, sales automation, and interactive assistants.
Machine Learning Project to align the mismatched subtitle (.srt file) of the movie!
Advanced AI assistant combining RAG, Gemini, hybrid BM25 + vector search, and Speech AI for intelligent document Q&A, semantic search, audio transcription, summarization, sentiment analysis, and conversational memory. Built with Python, Streamlit, Whisper, and Supabase.
🎙️ Production-grade multilingual AI Voice Assistant for e-learning. Bilingual EN/UR STT+TTS, Gemini Flash RAG, intent-based hands-free navigation & real-time admin analytics.
Verbomail is an open-source project aimed at revolutionizing email accessibility for individuals with visual and physical impairments. Verbomail empowers users to effortlessly manage their email communication.
speech to text converting program that using azure services and React framework
Developed a deep learning-based English-to-French translation system using Transformer architectures, supporting both text and audio inputs. Integrated speech recognition for audio-to-text conversion, enabling real-time translation for enhanced interlanguage communication and accessibility
Simple Node.js app: speech-to-text via whisper by OpenAI with file download.
Repository ini digunakan untuk proyek capstone program Laskar AI
To associate your repository with the speect-to-text topic, visit your repo's landing page and select "manage topics."