Back to Agents
Vakya-AI
Yasaswini38 August 15, 2025
6 copies 0 downloads
Vākya AI — A real-time AI voice agent that listens, understands and talks back . Powered by FastAPI, WebSockets, AssemblyAI, Gemini, and Murf AI.
Agent Definition
Markdown # Vākya AI 🗣️ Vākya, which means "sentence" in Sanskrit, is a conversational AI that allows users to interact with a Large Language Model (LLM) using their voice. Speak. Understand. Reply. That’s **Vākya** , a full loop of human-like conversation, built with **Python**, driven by **FastAPI**, and delivered in a crisp, modern UI. *** ## Wanna know How I look?? [](https://raw.githubusercontent.com/Yasaswini38/Vakya-AI/main/demo_vakyaai.mp4) *** ### Features * **Voice-to-Voice Interaction**: Talk to the AI and hear it respond back in real time. * **Real-time Transcription**: See your speech transcribed instantly on screen. * **Conversational Memory**: Maintains context within a session for natural dialogue. * **Session Management**: Start new chats or revisit past conversations. * **Voice Customization**: Choose from multiple voices for responses. * **Fun Skills Built-in**: Weather updates, News headlines, Jokes on demand. * **Modern UI**: Cute & aesthetic responsive interface with chat history panel. *** ### Technologies Used * **FastAPI** — backend framework for REST + WebSocket support * **Jinja2** — template rendering for frontend * **AssemblyAI** — speech-to-text (transcription) * **Google Gemini** — LLM for text generation * **Murf.ai** — text-to-speech (streaming natural voices) * **python-dotenv** — for managing API keys securely * **HTML, CSS, JavaScript** — responsive UI (with chat history, persona selection) *** ### Architecture The application follows a simple client-server architecture: 1. User’s voice recorded via browser microphone 2. Audio streamed to FastAPI backend over WebSocket 3. AssemblyAI transcribes speech → text 4. Transcribed text + history → Gemini (LLM) for response generation 5. Response text → Murf.ai → natural voice audio stream 6. Frontend shows transcription, AI’s reply, and plays back
Comments
More Agents
View allresearch
NotebookLM
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
G
Googlebrowser
Project Mariner (Browser Agent)
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
G
Google DeepMindmultimodal
Project Astra (Multimodal Agent)
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
G
Google DeepMindenterprise
Gemini Enterprise Agent Platform
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
G
Google Cloudresearch
Gemini Deep Research Agent
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
G
Googlecanvas
Gemini Canvas Agent
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.
G
Google