Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

Bulk call automation tool using Telnyx and LLM-based transcription. Dials, plays audio, records, and transcribes hundreds of concurrent calls via thread pooling.

Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)

Real-time AI ChatBot and voice-enabled AI VoiceBot using Deepgram (STT ↔ TTS) and Groq LLM for natural conversations.

Speak (speech-to-text) to LLMs (Ollama) in any lanaguage - Streamlit app https://deepwiki.com/iamaziz/llm-voice-bot

Get started using Deepgram's Voice Agent with this Node demo app

📞 Automated voice AI calling system using VAPI, n8n, and Airtable. Calls leads automatically, conducts natural conversations, and books appointments via Calendly. Multi-channel follow-up with email and WhatsApp.

Maxbot is an open source library and framework for creating conversational apps

A magical Christmas experience where Santa Claus (AI with Santa's voice) actually calls children on the phone

Amazon Connect Multi-Lingual ChatGPT Voice Bot via AWS Lex written in Java

Flask WebSocket proxy for Deepgram's Voice Agent API

An AI-powered voice bot to schedule appointments through phone calls, built with Flask, Twilio, and Gemini AI.

Chime SMA ChatGPT Multi Lingual IVR for Square Retail

Get started using Deepgram's Voice Agent with this Django demo app

Audio enabled end-to-end RAG pipeline

Get started using Deepgram's Voice Agent with this Go demo app

here you will find two NLP applications : Voice bot & Chat bot

Package for django onpage support bot with speech recognition and voice commands

Speech-to-Speech OpenAI Realtime VoIP Bot (SIP Extension) with Function Calling and External MCP Servers

Saya Voice Assistant for Discord AI voice bot: listens, detects keywords, chats via LM Studio, and replies with TTS or voice cloning.