voice-ai-agents

💼 Your own AI-powered voice interviewer for hiring.

Conversational voice AI agents

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.

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

Voice Prompts, GPT-4o prompts, Voice Agent Prompts, ChatGPT Prompts, HumeAI Prompts

A complete voice AI building block with telephony integration, featuring real-time speech-to-text, text-to-speech, and LLM-powered conversational agents.

Open-source observability and session replay for Pipecat voice agents. Replay conversation audio alongside OpenTelemetry traces, logs, per-stage latency, and interruption metrics.

Cross-platform audio capture, playback, VAD, AEC, audio conditioning, and multichannel support for Python and Node.js, powered by a Rust core.

voice ai agent that's able to do tool calls with composio integrations

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.

Benten is an audio evaluation and analytics platform built specifically for Voice AI agents. It connects directly to voice AI platforms to discover your agents, process call audio, and measure conversation quality, response latency, and speech dynamics.

Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.

Real-time accent conversion during phone calls using Twilio, Deepgram, and Google Cloud TTS

AI Customer Support Agent with RAG + Voice A fully local, privacy-focused AI customer support system powered by open-source models. It supports multi-turn conversations, PDF/manual search (RAG), product recommendations, FAQ reasoning, and voice input/output using local STT + TTS. Built with Mistral 7B GGUF, FAISS, Whisper Tiny, Coqui TTS, FastAPI.

Advanced speaker identification and verification system using deep learning. Features emotion recognition, language detection, and anti-spoofing capabilities for secure voice authentication applications.

A versatile, full-stack template for building AI-powered voice agents.

Voice AI agent for Ray-Ban Meta glasses using Amazon Bedrock AgentCore and Strands Agents

Open-source Python SDK for real-time Voice AI, voice agents, streaming audio, and observability using Rapida.

VoiceCare is an AI friend for our elders. They cared for you when you were young, so now let VoiceCare help keep them company and brighten their day.

InvertAI is a conversational AI platform designed for the hospitality industry. It automates guest messaging across various platforms, including WhatsApp, Instagram, and Facebook, using technology like ChatGPT and other large language models (LLMs). This helps hotels increase direct bookings and streamline their communication processes.