🏆 View Winners 🌟 View Sponsors 👥 All Participants

Bharath Munakala

Participant

Ultra Low Latency Voice AI Agent with Multi-Tool Support: Samantha

Votes0

Score0

🧠Community0×5= 0

🌐Public0×1= 0

Individual

December 4, 2025 at 07:22 PM

Project Demo

Submission Details

hear-about-us: Linkedin

name: Bharath Munakala

College / University Name: Godavari Institute of Engineering & Technology (GIET), NH-5, Chaitanya nagar, Velaguvanda Village, Rajanagaram(M),Rajahmundry,PIN- 533296 (CC-55)

linkedIn-profile: https://www.linkedin.com/in/bharathmunakala04/

Project Title: Ultra Low Latency Voice AI Agent with Multi-Tool Support: Samantha

Describe what your project does?: Samantha: Ultra Low-Latency Voice AI Agent An intelligent multi-modal AI assistant that delivers real-time voice and text interactions in under 4 seconds. Built with FastRTC, LangGraph, and Cerebras GPT-OSS-120B, Samantha combines ultra-low latency streaming with powerful agentic capabilities. What it does: Provides instant voice and text-based assistance with 7 specialized tools including web search, multi-PDF RAG, flight & hotel booking, stock analysis, and weather updates. Features both a Streamlit chat interface and FastRTC voice streaming for seamless user experience. Why it matters: Traditional AI assistants suffer from high latency (5-10+ seconds), making conversations feel sluggish and unnatural. Samantha achieves 3-5 second response times through optimized streaming architecture, making AI interactions feel as natural as talking to a human. The RAG system enables personalized responses based on user documents, while the multi-tool orchestration handles complex real-world tasks autonomously. Key innovation: Combines FastRTC's ultra-low latency audio streaming with LangGraph's intelligent agent orchestration, delivering production-ready conversational AI that's both fast and capable.

Share a 3–5 minute HD demo video: https://drive.google.com/file/d/1sC95OuhhmSgOsWDtGPVrAHsfCz8s2zdj/view?usp=sharing

Hosted Project Link (if any)

GitHub Repository (if any): https://github.com/Bharath8080/FastRTC_ReAct_Agent.git

artifacts/ supporting material: https://drive.google.com/drive/folders/1NpqgXskGBdZraMpDsEmWo0ujG-s2xncy?usp=sharing

Is this project your original and proprietary work?: Yes

Does your project include any private, sensitive, or restricted code or content?: No

Do you give us (AI Demos & partners) permission to feature your work on our website and share it with our community (with full credit)?: Yes

Do you consent to us showcasing your name/profile on our social media platforms and YouTube: Yes

Are you open to freelance, internship, or collaborative opportunities based on this project?: Yes, I’m interested

Comments (0)

Explore More

All Participants Hackathon Details

Get In Touch

Connect with Bharath Munakala to learn more about their project.

LinkedIn Profile

Featured

FutureSmart Agent

A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.

Samantha: Ultra Low-Latency Voice AI Agent An intelligent multi-modal AI assistant that delivers real-time voice and text interactions in under 4 seconds. Built with FastRTC, LangGraph, and Cerebras GPT-OSS-120B, Samantha combines ultra-low latency streaming with powerful agentic capabilities. What it does: Provides instant voice and text-based assistance with 7 specialized tools including web search, multi-PDF RAG, flight & hotel booking, stock analysis, and weather updates. Features both a Streamlit chat interface and FastRTC voice streaming for seamless user experience. Why it matters: Traditional AI assistants suffer from high latency (5-10+ seconds), making conversations feel sluggish and unnatural. Samantha achieves 3-5 second response times through optimized streaming architecture, making AI interactions feel as natural as talking to a human. The RAG system enables personalized responses based on user documents, while the multi-tool orchestration handles complex real-world tasks autonomously. Key innovation: Combines FastRTC's ultra-low latency audio streaming with LangGraph's intelligent agent orchestration, delivering production-ready conversational AI that's both fast and capable.