Voice & audio

Voice assistants & voice agents

995 agents · most starred first

Voice assistants & voice agents, page 6 of 10

livekit-rag-voice-agent★ 8

A comprehensive toolkit for building advanced, AI-driven conversational voice agents with a focus on Retrieval-Augmented Generation (RAG). This repository provides a flexible and powerful platform for creating intelligent voice assistants that can interact with users in real-time and provide context-aware responses based on a knowledge base of your

Pipecat-AI-Interview-Coach-Real-Time-Voice-Interaction★ 8

Develop a real-time AI-powered interview practice coach using voice interaction. This project involves building a full-stack system where users can practice interviews with an AI interviewer, receive intelligent feedback, and interact with an animated avatar.

VoicePal★ 8

an AI-powered chatbot app

30-days-of-voice-agents★ 8

Murf AI's 30 Days of AI Voice Agents Challenge

olami-python-voice-kit★ 8

OLAMI Voice Kit - Python sample codes for the voice-based assistant robot

Freya★ 8

An OpenAI GPT-3 AI chatbot frontend with speech-to-text and text-to-speech written in Python

OpenAI-RealtimeAPI-Voice-Assistant★ 8

Interruptible Chatbot Using Realtime API

livekit-voice-ai-agent-setup★ 8

The "livekit-voice-ai-agent-setup" repository provides a comprehensive guide and resources for setting up a voice-enabled AI agent using the LiveKit platform. It includes step-by-step instructions, code samples, and documentation to help users quickly deploy their own voice AI agent solutions.

composite-voice★ 8

Composite voice agent SDK with no extra infra requirements. Supports browser-native STT/TTS features.

fried-gpt★ 8

An android OpenAI/LLM voice assistant

MindBloomAI★ 8

MindBloom AI is an AI-powered mental health voice companion offering empathetic, real-time conversations in 11 Indian languages. Features crisis detection, mood tracking, guided breathing exercises, and therapy booking. Your gentle wellness guide. 🌸

fonos★ 8

Hotkey-first, local-first voice and text workflows for macOS & Linux. Build reusable recipes with speech-to-text, LLM prompts, text-to-speech, and desktop actions, then run them in any app using local or cloud models.

composite-voice★ 8

Composite voice agent SDK with no extra infra requirements. Supports browser-native STT/TTS features.

openclaw-whobot-skill★ 8

OpenClaw WhoBot Skill — WhoBot (呼波特) AI电话数字员工知识技能,为 OpenClaw AI 代理注入 WhoBot 全量知识 | OpenClaw knowledge skill for AI Phone Digital Employee platform

banshee★ 8

Give your AI coding agent a voice. Speak to it, hear it back, fully on-device.

amos2026ss04-taskorbit-conversational-agent★ 8

Conversational AI Agent & Multi-Agent Workflow Orchestration Platform

voice-ai-agent-basic★ 8

Voice AI agent with basic capabilities including telephony

Aura★ 8

说出想法,Aura 用本地语音识别、可配置 LLM、任务模式和 Skill 匹配,将它整理成可直接交给 AI Agent 执行的清晰任务。

dsh-plugin-call-me★ 8

Your DeepSeek Harness agent rings your actual phone: it asks out loud, you answer out loud, and what you said steers the run.

Friday★ 8

An open-source, voice-activated AI companion for developers. Built with Tauri and Python, featuring workspace context and multi-LLM support.

Fasal-Pramaan★ 8

Introducing Fasal Saathi - our agentic voice co-pilot that files crop-loss claims in 15 Indian languages. It navigates, shoots, and submits. On-device anti-spoof vision + satellite ground-truth. A human still decides. Nothing auto-pays.

sonitura★ 8

A voice assistant that sees your screen — hold a key, ask, and it answers out loud on the ChatGPT plan you already pay for. Local speech-to-text + neural TTS, on-screen agent, private local memory. Open source, macOS.

genpark-realtime-voice-turn-taking-orchestrator-skill★ 8

Sub-100ms conversational turn-taking & barge-in handler (Cartesia Sonic / ElevenLabs)

Voice-Agents★ 8

Voice-Agents is a production-ready Python library for building enterprise-grade voice-enabled AI applications. Built by Swarms Corporation, it provides seamless integration with multiple TTS/STT providers including OpenAI, ElevenLabs, and Groq, with real-time streaming capabilities optimized for agent-based architectures.

genpark-multimodal-audio-emotion-valence-detector-skill★ 8

Acoustic vocal emotion, prosodic valence, and customer frustration analyzer

genpark-multimodal-voice-prosody-sentiment-analyzer-skill★ 8

Multi-modal speech prosody and vocal sentiment analyzer detecting speech rate, pitch variance, and user cognitive fatigue to dynamically calibrate agent response pacing.

genpark-phone-agent★ 8

Local voice agent for inbound call centers.

genpark-voice-pm★ 8

An autonomous voice-to-action agent. Transcribes voice notes, extracts action items, and schedules them natively.

thymia-sentinel-integrations★ 7

Beta Product - Integration examples for Thymia Sentinel, a real-time voice biomarker and safety monitoring service for voice AI agents.

clarion★ 7

Your agents have things to say. Now they have a voice to say them with.

caseAI★ 7

caseAI is a voice-to-voice AI assistant utilising OpenAI's GPT and Whisper APIs.

Echo★ 7

Voice-to-voice LLM conversation, Full-local

Multi-Functional-AI-Assistant★ 7

An advanced AI assistant that can make object detections and uses dialogpt model, Nvidia RIVA for NLP, TTS, STT and multiple APIs from 10 different sources.

chatapp-with-voice-and-openai★ 7

This project uses OpenAI's GPT-3 model to create a simple assistant that can interact with you via speech or text

RabbitR1-Strom-Chatbot★ 7

Chatbot System

voice-agents-demo★ 7

AI-powered outbound calling chatbot built with Twilio, FastAPI, and Pipecat, supporting real-time voice streaming and LLM integration.

vilberta★ 7

Voice chatbot with voice+screen output to show that "not everything needs to be spoken"

dialtone★ 7

Give your AI agent a mouth, ears, and a phone number. Framework-agnostic VoIP/IVR service with Twilio — plug in any agent backend (Hermes, OpenAI, Ollama, etc).

seneschal-voicebot★ 7

Voice chatbot to use your personal AI agents.

AI-voice-assistant-with-RAG-powered-customer-support★ 7

Enterprise-grade AI voice assistant with RAG-powered customer support, real-time phone integration, and advanced conversation management

genpark-voice-turn-taking-endpoint-detector-skill★ 7

Energy and transcript heuristics for voice turn endpoint detection.

genpark-realtime-voice-cross-talk-suppressor-skill★ 7

Full-duplex voice agent echo suppressor distinguishing user barge-in from speaker playback acoustic feedback

genpark-realtime-voice-vad-silence-trimmer-skill★ 7

Voice Activity Detection (VAD) audio silence boundary trimmer eliminating latency overhead

standin★ 7

StandIn: put your AI agent into Microsoft Teams calls as a real participant, in your own tenant. agent backends (OpenClaw, Hermes Agent, LiveKit, ElevenLabs, OpenAI Realtime, Deepgram, Cartesia)

iris★ 6

A voice assistant that can recognize and respond to user’s voice commands using Porcupine, Whisper, pyttsx4, OpenAI GPT, and LangChain.

KoroMind★ 6

Koro — voice-first AI agent that actually does things. Search, code, execute — all via Telegram voice.

AI-Medical-Voice-Assistant★ 6

AI chat/voice assistant designed to calculate medical scores

sam2webappvoiceagent★ 6

Video and Voice Agent for SAM 2 Web App

Voz-AI★ 6

Voz-AI is an AI-powered RAG based voice assistant that is designed to help customers inquire about queries and retrieves the most accurate and relevant information back to them. This project was made for the AIQoD Hackathon 2025, eventually winning us the runner-up position.

Voice-Based-Native-Language-Service-Agent-★ 6

🤖A Voice-First Agentic AI for Government Schemes in Hindi. Built with LangGraph (State Machine), Groq (Llama-3), and EdgeTTS for low-latency, CPU-optimized inference without GPUs.

advanced-voice-agents-SDK★ 6

Voice Agent SDK helps you build realtime voice agents with prompts, tools, knowledge, providers, and guardrails, so your AI doesn’t wander into the conversation like it just got promoted by accident. Structured enough for production, flexible enough for weird ideas, and smart enough to ask before doing something expensive.

jevme★ 6

Talk to your Mac and it does it — in any app, while you're still talking. Open-source voice agent that gets faster the more you use it.

voiceloop★ 6

Fast, interruptible browser voice agent: VAD → STT → LLM → TTS with real barge-in, echo filtering, streaming TTS and tap-to-seek. Zero runtime dependencies.

LLM_telecenter★ 5

A fastapi wrapper of babca / python-gsmmodem for a waveshare sim7600x. Not an exact copy of the 'python-gsmmodem' so be sure to uninstall that lib or venv to run | Open-source Twilio with LLM batteries

MockFlow-AI★ 5

Voice-based mock interview platform featuring intelligent conversation management and time-aware stage transitions

GPT-Discord-Chatbot★ 5

Discord chatbot powered by OpenAI and ElevenLabs that enables natural and engaging conversations with users in text and voice.

Hamster-Bot-Prototype★ 5

Rudimentary Chatterbot written in Python

Speak_with_ChatGPT★ 5

Simple python-only code to have a voice conversation with ChatGPT.

speak-gpt-lite★ 5

Your personal voice assistant based on OpenAI ChatGPT focused on privacy.

VoiceCordAI★ 5

A Discord bot for hands-free voice conversations with LLMs in Discord voice channel.

Voice-Chatbot★ 5

Voice Chatbot, Course Project, Speech Processing

chatbot★ 5

A fast customizable Text-To-Speech Chatbot built using Java, JavaFX, Ollama API and Silero-TTS

learn-aws-voice-calling-chatbot★ 5

Automated Voice Calling Chatbot in AWS using Amazon Connect, Lex, Polly, and Lambda

siteware-backend-v2★ 5

Siteware Backend - German Voice AI Agent provider - Deepgram + Twilio + Elevenlabs + OpenAI + Pinecone

AI-Calling-Agent★ 5

An automated calling solution that uses AI to make sales calls for Call Worklog AI product, assist with customer queries, and update customer information in a database.

golden-medical-voice-agent★ 5

An end-to-end voice AI agent built with LiveKit, Twilio, Deepgram, OpenAI, and AWS Polly. This agent receives voice calls, understands user goals, gathers required information, and stores results in Google Sheets.

Voice-Assistant_OpenAI★ 5

This is a Voice Assistant like Google-Assistant or Alexa using Open AI's ChatGPT. This project is developed using Python & Gradio on Google Colab.

chloe★ 5

Chlo-e: A voice-activated AI friend powered by OpenAI's GPT-3.5 Turbo, Porcupine hotword detection, and Google's Text-to-Speech. Engage in realistic spoken conversations.

realtime-ai★ 5

Real-time AI voice conversation platform with WebSocket, supporting streaming STT/LLM/TTS

Simultaneous-Interpretation★ 5

Simultaneous-Interpretation is an advanced tool for real-time simultaneous interpretation. It transcribes and translates spoken language from a microphone input instantaneously, continually refining translations for accuracy. Ideal for business meetings, educational settings, and live events, it enhances multilingual communication effortlessly.

AI-Voice-Assistant★ 5

In this project, I will build a virtual assistant that asks and answers through voice, using Livekit and OpenAI. In addition, I also set a number of separate tasks so that the assistant can respond and adjust according to my wishes.

nova-voicebot-api★ 5

Express + TypeScript API for Nova, a voice/text chatbot: text completion with the OpenAI API and speech synthesis via VoiceRSS.

WaveSlayer★ 5

ai chatbot that uses speech to operate and respond

VoiceAssistanceChatApp★ 5

AI Voice Assistant using Flutter , OpenAI and the bot supports four languages: English, Kannada, Tamil, and Telugu. It responds to predefined personal questions with context-aware answers and fetches live data for queries

voice-agent-asterisk★ 5

AI-powered voice assistant integrated with Asterisk PBX. Uses OpenAI for natural language processing and provides intelligent phone interactions.

android-azure-speech-openai★ 5

An integration of Azure Speech Service and Azure OpenAI in Android. This repository demonstrates a pipeline where speech from the microphone is first converted to text using Azure Speech Service. The resulting text is then passed to the Azure OpenAI service, which generates a response to the provided prompt.

hse-emotion-assistant★ 5

Multimodal emotion assistant with visual emotion analysis, Qwen realtime voice interaction, and local RAG knowledge base.

Agora★ 5

Agora — Real-time voice rooms where humans and AI agents collaborate across platforms

Leo-Ai-Assistant-2.0★ 5

Leo is a 3D interactive AI assistant built with React Three Fiber, ElevenLabs, and Blender models. It features real-time voice interaction, lip-sync using Rhubarb, and a sleek, lifelike avatar for immersive communication.

Voice-first-ChatGPT★ 5

Voice-first ChatGPT companion that fuses multilingual speech recognition with lifelike AI synthesis directly in your browser.

TTS_Twilio_GPT★ 5

Automatic answering system. chatbot with ChatGPT and Twilio

Discord-Voice-Channel-Bot★ 5

A bot that can join voice channels using the OpenAI api and Microsoft's free Text-to-Speech (TTS) services. The bot can transcribe conversations, generate intelligent responses, and communicate verbally within your voice channels.

VoiceGuard★ 5

🛡️ Advanced Voice Authentication System using OpenAI ChatGPT & Whisper APIs. Secure voice biometric identification with AI-powered analysis, multi-sample enrollment, and enterprise-grade authentication logging. Python-based with SQLite database.

source-persona★ 5

♊ Voice-Interactive AI Digital Twin powered by Google Gemini 3. Talks to recruiters via Neural TTS, visualizes architecture, and defends against prompt injection.

visionclaw★ 5

🦐 VisionClaw — Interactive 3D AI companion for Apple Vision Pro. Voice-powered conversations with an animated character in mixed reality. Built with RealityKit, SwiftUI, and SFSpeechRecognizer.

openclaw-voice★ 5

AI-powered Discord voice bot with natural conversation, smart turn detection, and OpenAI-compatible TTS/STT

Multi-Voice-AI-Assistant★ 5

Voice Chat AI is a project that allows you to interact with different AI characters which is modular using speech. You can choose between various characters, each with unique personalities and voices. Have a serious conversation with Albert Einstein or role play with the OS you can use it for voice

voicecheck★ 5

End-to-end testing for voice agents. YAML scenarios, real audio through LiveKit/Daily/VAPI/Retell, and 13 evaluators for latency, tone, and roleplay consistency.

swiss_german_gemini★ 5

Real-time Swiss German voice chat application supporting 8 dialects. Multi-AI provider support (Groq, Gemini, OpenAI) with optimized latency pipeline.

Audio-Agent★ 5

gradio agent-demo-track region:us

VoiceToVoice_ChatBot★ 5

gradio region:us

Voice-Assistant-AI★ 5

gradio region:us

skills★ 5

Agent Skills for the Patter SDK — give your AI agent a phone number. Works in Claude Code, Cursor, OpenClaw, Hermes Agent, Codex, Cline, Goose, Amp, Windsurf, and any harness that consumes the Agent Skills standard. One CLI: npx skills add patterai/skills

atticus★ 5

A framework-agnostic voice agent library for voice-controlled UI interactions, powered by OpenAI's Realtime API.

voicebridge★ 5

Voice teammate for Claude Code: talk to your live session hands-free, hear replies spoken. Local whisper STT + macOS TTS. /voice-on in any session.

xiaozhi-go★ 5

Build your own AI friend.

rode★ 5

Rokid AR glasses voice → your own AI brain (default Claude); glasses-native app + self-hosted backend, pluggable brain/STT/ingress. | Rokid 眼镜语音 → 你自己的 AI 大脑(默认 Claude);眼镜原生 app + 自建后端,大脑/STT/公网入口可插拔。

vinga★ 5

Conversational AI. Sweded. A self-hostable home for voice agents: mix and match the LLM, voices, and MCP tools that fill every stage, spoken through small ESP32-S3 boards.

OpenVoice-AI★ 5

Real-time, multi-agent AI voice assistant with animated visual feedback. Built with LangGraph Swarm, FastAPI, WebSocket streaming, and React.

SmartCall★ 5

AI 驱动的智能客服呼叫中心系统,让每一通电话都被智慧对待

More in Voice & audio