Audio agents

Open-source AI DJ co-host. Listens, watches, talks back.

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.

Give your Hermes agent a body — an animated face, live RGB presence, and mood, all driven by the agent's real state. Minnie is the flagship example.

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

TRTC AI Integration Assistant - helps developers integrate Tencent Real-Time Communication SDKs (Chat, Call, RTC Engine, Live, Conference) across Web, Android, iOS, Flutter, and Electron.

Documented case of Claude Opus 4.6 entering an infinite generation loop in Cursor. 3,400 lines, 294 self-termination attempts, full transcript and recordings

Just A Rather Very Intelligent System

A turnkey, fully-local AI workstation engineered for the AMD Ryzen AI Max+ 395. LLM inference, voice, document parsing, browser automation, agents — all on-device.

Transformative Evolving Neural Kinetic Agent - a local-first Python voice agent for Windows.

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).

gradio Agents-MCP-Hackathon mcp-server-track region:us

gradio region:us

gradio region:us

Swift-first toolkit for shipping on-device AI on iOS, macOS, visionOS, tvOS and watchOS — Core ML LLM runtime with SwiftUI prefabs, structured output, tool calling, RAG and speech.

The complete AI chat toolkit for Flutter — streaming, tools, generative UI, voice, and a batteries-included UI kit. Provider-agnostic (OpenAI, Anthropic, Gemini), state-manager-agnostic. The Flutter answer to Vercel's AI SDK + AI Elements.

Local-first AI clipping studio - turn long videos into ready-to-post vertical Shorts entirely on your own PC. Multimodal clip detection, speaker-aware face tracking, editable captions, AI edit chat. No cloud AI, no fees.

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

Open-source web dashboard for Vexa – manage meeting transcriptions, view real-time transcripts, and chat with your meetings using AI.

Just A Rather Very Intelligent System

✨ Instant timestamped chapters for your YouTube videos with just one click! ✨

Nicolay is a digital history experiment that uses artificial intelligence to explore the speeches of Abraham Lincoln.

LLM agent that provides tools for convenient work with personal documents using voice or text.

A Streamlit app for document question answering and text summarization.

A powerful Streamlit app that enables seamless interaction with multiple large language models (LLMs) using various media inputs, featuring advanced options for multi-modality, voice responses, chat, summarization, and agent-based tools.

全双工语音对话驱动的 PPT 生成助手。语音/文字交互 → AI收集需求 → 自动生成 Slidev/PPT → 语音反馈修改。双 Agent 架构，单卡 RTX 4090 可跑全链路。开源代码 + 数据集 + 模型权重。

AI-powered YouTube video summarizer using GPT-4/Gemini - Extract transcripts and generate concise summaries with key points

Video and Voice Agent for SAM 2 Web App

A virtual co-host that makes presentations a breeze by using AI to read out your slides, freeing you from prep hassles and letting you focus on delivery

🏠🤖 HomeAssistant Add-on for Claude Desktop MCP integration. Control smart home devices, create automations, and manage your home with natural language through Claude.

MCP server for VOICEPEAK text-to-speech synthesis

Dify智能体 RAG统计分析课程助手 TTS文本转语音

Self-hosted multi-user AI assistant with agents, memory, scheduler, ESP32 voice satellites, and a built-in dashboard. Works with Claude, OpenAI, Ollama, LM Studio, and more.

NVIDIA DGX Spark ressources

Meeting AI assistant, records, transribes, auto generated summaries, can also use llm agent to send summaries as mail or push to a notion page.

An AI-powered backseat coach to fix your skill issue and/or ruin your day :). Supports popular models from OpenAI, Anthropic and Google and self-hosted. Customizable prompting and voice cloning thanks to ElevenLabs and Coqui TTS.

Scribo CLI — the official npm package for generating EN 16931-compliant e-invoices (ZUGFeRD, XRechnung, plain US PDF) from the terminal and CI. Install: npm i -g @causaprima/scribo-cli

🎙️🧠 Local-first macOS meeting + document notebook — on-device Whisper transcription, source-linked notes, @brain and history Q&A, a read-only local MCP server, E2EE sharing, and plain Markdown exports. Run AI locally or explicitly opt into redacted cloud AI · AGPL-3.0

gradio mcp-server-track speech-to-text whisper groq transcript api stt

gradio region:us

Gesture + voice control for macOS. Pinch to move cursor. Swipe for arrows. Circle to screenshot. Speak to run commands.

Self-hosted AI accountant. Reads receipts / invoices, reconciles ledgers, checks its own numbers, and asks before anything irreversible. Open source, agentic, runs on your infrastructure.

Talking While Acting: a fast/slow dual-model agent that holds a real-time phone conversation while autonomously operating a computer. System, VoiceComputerBench benchmark, and paper.

Local prompt-cache economics for LLM agents: split cache reads/writes from input spend, reconcile dollars to invoices, and surface concrete TTL/marker fixes.

The Tiledesk Automation Engine: Your open-source solution for multichannel workflow automation. An alternative to Voiceflow, Botpress, Stack AI, Flowise, Gumloop, VectorShift, Lyzr AI

A comprehensive interview platform that leverages AI to conduct voice-based interviews, providing recruiters with detailed insights and candidates with a seamless interview experience.

Model Context Protocol server for Plutio — CRM, projects, invoices, proposals, forms, time tracking & scheduling for Claude and other MCP clients.

A curated collection of real-world AI failures, mishaps, and cautionary tales. This project documents when AI systems go wrong, from chatbots giving bad legal advice to voice assistants accepting impossible orders.

MirrorBuddy - La Scuola Che Vorrei: AI-powered educational platform with voice tutors for students with learning differences

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

AutoTask: a novel LLM framework to execute user commands by exploring and learning from mobile GUI.

Voice-first Agentic AI Productivity Suite & Management Platform

This project demonstrates the power of AI-driven agents using the LangChain framework. It showcases the development of AI agents that can interact with various tools, perform web searches, fetch real-time information, and take notes autonomously based on voice commands or text queries.

Automate tasks with specialized AI Agents using CrewAI, Langchain and LLMs, a team of agents that can work together to complete tasks using AI prompting techniques from creating tasks to generating keynote speeches.

🤖VChat-BigDL: A ChatBot for Video Understanding Based on BigDL

An app that summarises and answers questions about arbitrary YouTube videos using LangChain and LLMs

AI-powered ATC training platform with voice recognition, intelligent virtual pilots, and X-Plane 12 visualization

J.A.R.V.I.S is a smart, lightweight, and extensible voice assistant that runs directly on your phone. Built with React Native and integrated with OpenAI's powerful language model!

JANE - An intelligent personal virtual assistant with voice control, AI conversations, system automation, and adaptive learning.

A powerful desktop assistant built in Python that combines voice commands, GUI interface, and system automation capabilities.

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

Rudimentary Chatterbot written in Python

A multi-language virtual assistant

Python Contextual Chatbot with Voice Recognition.

Chatbot with text-generation-webui and ChatGPT 3.5 backend with a sort-of long-term memory.

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

TypeScript-фреймворк для разработки голосовых навыков и чат-ботов. Он даёт единую бизнес-логику для всех платформ — но одинаково эффективен, даже если вы работаете только с одной. Поддерживаются: `Яндекс.Алиса`, `Маруся`, `Сбер Салют`, а также `Telegram`, `VK`, `MAX` и `Viber` из коробки.

Matrix bot to collaboratively queue music on Spotify

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

Voice Chatbot, Course Project, Speech Processing

:speech_balloon: An AI bot for IRC written in Ruby

ChatBot per pagamenti vocali (prototipo)

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

A Python tool that transcribes video and audio files to text using Whisper, with ChatGPT-powered summarization

Transcriptr is a modern web application that converts audio files to text using artificial intelligence. It provides a clean, intuitive interface for uploading audio files and receiving high-quality transcriptions powered by Replicate's Incredibly Fast Whisper model.

🔊 PiperGen: Pretrain Piper TTS with OpenAI voices! Capture, convert, and fine-tune models for rich, natural speech synthesis. 🗣✨

AI project to suggest artists suggestion based on music style or influences - chatGPT-4o - Symfony7

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.

Transforme áudios do WhatsApp em prompts estruturados prontos para qualquer LLM.

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.

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.

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.

TechSphere's Interview Assessment System is a collaborative web app created with React.js, React-Router, Chart.js, and React-Chartjs-2. Developed by a dedicated team of five members in just two days, it empowers users to choose courses, answer interview questions using speech recognition, and receive valuable feedback.

ai chatbot that uses speech to operate and respond

Authenticating with Entra ID (former Azure AD) to access Azure OpenAI models in Python SDK v1.x

跨平台桌面语音输入工具 / Cross-platform voice input app with real-time HUD, ASR, LLM correction, and text injection

A quick access popup window for advanced text operations. For desktop and Android.

AI assistant that reads you whatsapp conversations and audio messages, and suggests a response based on your tone (can also send audio messages)

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

Resume is a small CLI that reconstructs your last working session.

A modern, AI-powered YouTube Video and Audio Downloader built with Python. Features automatic AI tagging, FFmpeg video slicing, and an Advanced HTML5 Subtitle Manager.

🧠 [ACM-TORS] A Resource for Multi-Modal Learning in Visual RAGs

VoiceAudition — the voice casting director for AI agents. Cross-provider TTS voice discovery and recommendation.

An advanced AI mental health assistant that combines voice interaction, fine-tuned psychology models, and intelligent knowledge retrieval to provide comprehensive psychological support.

Self-hosted AI platform — 47+ microservices, 20 messaging adapters, native apps, enterprise multi-tenancy, zero cloud dependency

Agentic Proposal Generator: Multi-agent AI system using Claude Agent SDK that converts B2B discovery call transcripts into business proposals.

🐙 Integrate Home Assistant with n8n to run conversation agents, expose AI tasks via webhooks, and share context to n8n for smarter automations.

Fully offline iPhone meeting memory. Zero network calls, no Wi Fi required. Records, transcribes, summarises, and answers questions entirely on device. Audio, transcripts, summaries, embeddings, and chat never leave the phone.

Open-source adversarial simulation and evaluation harness for conversational AI agents.

Open-source AI memory engine for agents: multimodal memory, temporal knowledge graphs, graph RAG, and evidence-backed long-term context.