QuickAgent  by gkamradt

Voice bot demo using speech and language models

created 1 year ago
371 stars

Top 77.4% on sourcepulse

GitHubView on GitHub
Project Summary

QuickAgent is an alpha-stage Python demo showcasing a voice-controlled chatbot. It integrates Text-to-Speech (TTS), Speech-to-Text (STT), and a Large Language Model (LLM) for conversational interaction, targeting users interested in real-time voice AI applications.

How It Works

The bot leverages streaming audio processing for both STT and TTS to minimize latency. It's configured to use Deepgram for audio services and Groq for its LLM, enabling a fluid, conversational experience. The core logic is contained within the QuickAgent.py script, with reusable components in the building_blocks directory.

Quick Start & Requirements

  • Primary install / run command: python3 QuickAgent.py
  • Prerequisites: Deepgram API key, Groq API key.
  • Setup time: Minimal, assuming API keys are readily available.

Highlighted Details

  • Utilizes streaming for STT and TTS for reduced latency.
  • Integrates Deepgram for audio processing and Groq for LLM.
  • Demonstrates a conversational voice bot architecture.

Maintenance & Community

No specific community channels, contributors, or roadmap details are provided in the README.

Licensing & Compatibility

The license is not specified in the README.

Limitations & Caveats

This is an alpha demo, indicating potential instability and incomplete features. The project relies on specific third-party services (Deepgram, Groq) which may incur costs and require API key management.

Health Check
Last commit

1 year ago

Responsiveness

1 week

Pull Requests (30d)
0
Issues (30d)
0
Star History
8 stars in the last 90 days

Explore Similar Projects

Starred by Thomas Wolf Thomas Wolf(Cofounder of Hugging Face), Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), and
2 more.

ultravox by fixie-ai

0.4%
4k
Multimodal LLM for real-time voice interactions
created 1 year ago
updated 4 days ago
Feedback? Help us improve.