Get started using Deepgram's Live Transcription with this Node demo app

Get started using Deepgram's Transcription with this Node demo app

A speech recognition library running in the browser thanks to a WebAssembly build of Vosk

A futuristic personal portfolio featuring a voice-activated AI assistant powered by Google Gemini. Built with React and Three.js, it offers an immersive cyberpunk experience with real-time voice interaction, dynamic 3D visualizations, and context-aware responses about skills and projects. Users can naturally converse with the AI to explore.

Transcription and annotation interface for recorded audio or video files

Lightweight local voice-chat API using VOSK STT, Ollama LLM, and Kokoro TTS. Includes FastAPI backend, web UI, and optional Caddy HTTPS.

Audio/Video file transcription to text file

AI voice assistant with visualization aspect

Chatbot with a 3D avatar that can answer interview questions in your behalf. It can speak and understand English, German and Albanian. Based on the GPT 4 model and Azure Speech to Text and Text to Speech, it is able to make realistic conversations about a job interview and save conversations.

Open source Speechify alternative. Read PDFs and EPUBs with local models.

AI-powered farming assistant built with React + Flask that helps farmers through multilingual chat, voice, and image-based crop disease detection using Google Gemini and Groq APIs.

Talk to an LLM, using your voice and hear it talk back!

Elora is a voice-based virtual receptionist for salons powered by the LiveKit Agents Framework. It enables natural conversations with clients, retrieves precise answers from a knowledge base using RAG-based retrieval, and escalates unknown queries to human supervisors — all while continuously learning from resolved interactions.

Transcribe anything localy, fast and safe.

Browser-based open-source tool for creating high-quality TTS/STT datasets. Features AI transcription, multiple export formats, and audio visualization with no server-side processing. Perfect for ML engineers, developers, and researchers.

KisaanCredit is a full-stack 'Soil to Sale' ecosystem that digitizes and democratizes the carbon farming market for India's smallholder farmers

The TTS Engine is a sophisticated web-based platform designed to transform written text into speech that sounds remarkably natural.

A program I made so I could talk to someone ;(

A web application that converts speech to speech 100% private using VAD (voice activity detection)

Asistente personal web con entrada por voz (STT), salida por voz (TTS) y streaming de respuestas desde un modelo de lenguaje