Audio agents

🎤 A real-time voice AI assistant built with Next.js and deployed on Cloudflare Workers. Features voice activity detection, speech-to-text, AI conversation, and text-to-speech with WebSocket communication and Durable Objects for seamless voice interactions.

JAIvus is a ChatGPT powered personal assistant implemented in python and deployed as streamlit app

A part of speech tagger written in PHP.

Voiceflow Wordpress plugin

Chat Application using LLMs and Whisper for Speech-To-Text. Integrating Sherpa-ONNX for Text-to-Speech Support.

Simple chatbot using IBM Watson (STT, TTS, Assistant)

A Messenger Chat bot in which a resume will be generated based on a couple of questions asked by the bot :robot: :speech_balloon:

O assistente que aprende a fazer o que você pede. Open source, em português.

Open-source multi-tenant AI agent platform. Docker isolation, multi-channel, SIWE auth. Built on OpenClaw + Base. Our token is community-run. Agentbot builds the platform, while the market belongs to the community.

Open-source AI platform for personalized conversations — embeddable chat widget, pluggable LLM engines, PII redaction, voice I/O, and admin-driven intent & preset personalization.

A powerful and versatile AI-powered PBX for Asterisk, WhatsApp, Telegram, with text and audio support, built on Tibula.

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

Tiledesk is the open source AI agent builder, written in Node.js and Angular. This repository is dedicated to the WebApp dashboard to manage Tiledesk: open-source alternative to Voiceflow, enabling easy creation of advanced LLM-powered Agents with seamless human-in-the-loop (HITL).

Teron AI - advanced AI assistant by Zeyan Ramzan. Offers chatbot, question answering, jokes, music, Wikipedia search, alarm setting and more. Dual voice options, YouTube video download and open for commits. Improve productivity and have fun with Teron AI.

EdgeVoice 是一个使用.NET开发的适合Linux开发板的AI 语音聊天机器人。EdgeVoice is an AI voice chatbot developed with .NET, suitable for Linux development boards.

A voice chat assistant which allows you to speak with your machine

eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search with a chat that uses gpt-40-realtime audio

Turn Feishu/Lark into a remote control for Cursor AI — your personal AI strategic partner via IM

Japanese meeting transcription & minutes generation app with local ASR (Kotoba Whisper) + LLM (Ollama) + RAG. Privacy-focused, runs offline on CPU.

The first Minecraft AI that doesn't just talk—it lives in your world. High-performance Gemini-driven cognitive companion for Fabric 1.21.1.

Voice-based AI interview coach — feed it any job description in your language, practice in a fully controlled session, and get instant English-fluency and answer-quality feedback the moment you're done.

An awesome dicord bot

Run, fine-tune and serve real LLMs entirely in-process in .NET — on the CPU, on-device, offline. No Python, no GPU, no cloud.

Voice Agent implementations for the VAmoS Benchmark

Experimental voice user interface (VUI) to interact with an agentic AI assistant

Your personalized museum tour guide!

:sunglasses: Simple ChatBot, which replies to anything you ask ! Now with voice recgnition ! Say "Hey" to wake the bot ! :D

SpeakingAI is a demo of privately deployable 'GPT-4o like AI + RAG', a fully functional web AI server with audio query/answer in streaming, using LLM and RAG for backend knowledge.

Offline voice agent framework for robots — agents, skills, workflows, sub-second voice pipeline, 2D/3D simulation (IR-SIM + MuJoCo), 16 languages, 56 voices, ROS2-native. Runs on CPU/CUDA/Metal, no cloud.

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

Building AI products solo while traveling the world · Core contributor @openimsdk · Voice AI & Agents · cubxxw.com

A universal git-native AI agent framework — written in Rust. Single binary. Zero dependencies. 383 models. Blazing fast.

A full-stack application that allows practitioners to record voice notes and also export them to Google Docs/Sheets.

Voice Assistant AI This project is a high-performance, action-oriented voice assistant that uses ElevenLabs Conversational AI to provide human-like vocal interaction. It enables users to perform digital tasks—like building websites or creating art—entirely through natural speech.

Have a conversation with chatGPT. speech-to-text and text-to-speech is here using chatGPT

Node.js app where you can ask questions to ChatGPT using voice prompts, see the ChatGPT-like word-by-word answer, and then listen to the responses with voice

Voice calling plugin for OpenClaw — give your AI agent a phone number. Inbound/outbound calls, batch calling campaigns, SMS, post-call transcripts & notifications, ElevenLabs + Deepgram voice engines.

Patterns and insights about yourself, picked up your Wispr Flow chats

基于多AI协同的智能对话模块，让AI像真人一样自然参与聊天

Build your own local-first digital lifeform: an AI companion with memory, soul, multimodal perception, proactive dialogue, and auditable execution.

ACE Step 1.5 XL music generation with dynamics-preserving mastering. Part of the AEON Media Production family.

Make any web app voice-controllable in 37 languages. Drop-in widget + open-source agent server — visitors speak, the agent talks back and drives their browser in real time.

Webagent, Turn your website Into an AI site. Press Cmd/Ctrl+K to do anything — command palette, DOM-grounded agent, voice, inline AI, and Dwell long-press in one SDK. Ships with your product, not as a chatbot widget.

OpenAI Sora 2 — full premium build for Windows with pro features unlocked. Creative Suite Pro Pack

蓬莱 Penglai — TypeScript Host + Pi 核心的本地 AI 工作台 · Desktop / CLI / Feishu / WeChat

Suno AI Premium — text-to-music generator with vocal synthesis, genre control and commercial licensing for creators producing original songs.

本地优先的中文语音 AI 管家——说一句话，它替你操作 Windows（GLM-5.2 Agent + 本地 Whisper + GUI 自动化）

KI Operating System — Local-first AI infrastructure. Multi-Agent Orchestration, Ghost Control, One Voice Engine.

Self-hosted Rust LLM gateway for the Rabbit R1. WebSocket streaming, sandboxed Python agents, OpenAI / Anthropic / OpenAI-compatible providers.

ATRI 是本地优先的 AI Agent 架构与音乐工作站，提供多模型 LLM Runtime、工具调用闭环、上下文压缩、子 Agent 并行调度、MCP/Skills 扩展。并融合 Web DAW、MIDI 工程编辑与 Rust 实时音频/VST 宿主，让 Agent 能直接读写工程、生成 MIDI、控制播放并协作创作。

🔮 quami.io | Kwami's web2 platform

Inquiry videos with ChatGPT

🤖🎙️ Explore Lex Fridman Podcast Transcripts with a smart chatbot!

Infrastructure IA distribuée Linux — cluster GPU on-premise, 900+ agents autonomes, RGPD natif

An application that converts PowerPoint slides into videos and adds voice or text explanations automatically.

An AI-enabled music curation software suite based on Python and PydanticAI, utilizing Spotify and Brave Search as well as YouTube.

Edison - The Voice Controlled AI Assistant and Clock Radio

CursedGPT leverages the Hugging Face Transformers library to interact with a pre-trained GPT-2 model. It employs TensorFlow for model management and AutoTokenizer for efficient tokenization. The script enables users to input prompts interactively, generating text responses from the GPT-2 model.

Emilia - Desktop Character.AI Client

Integrate ChatGPT, Dall-E, Whisper and other AI models in Replicate into Messenger and Telegram bot

This is a personal health care tools.

🔒 A bot to log and prevent hate speech across many servers on Discord

Discord bot for Google and Polly Text-to-Speech

A turnbase mmoprg chat based game with 3 wifus.

A sample Nuxt 3 application that listens to chatter in the background and transcribes it using the powerful OpenAI Whisper, an automatic speech recognition (ASR) system.

Faster-whisper一键启动整合包带GUI界面

A web app to explore the life, works and world of famous composers through the years

Enhanced version of sora-extend with Docker support and CLI arguments. Original by @mattshumer_

MediBot AI; Your not-so-human, never-on-vacation, slightly overqualified AI medical assistant. Built with Ollama + RAG for brainpower, Whisper to hear your complaints, and React to look good while doing it. Finds hospitals, books appointments, tracks your cholesterol like a judgmental auntie, and soon might even talk back in your language.

Perl Framework for AI - Langertha - the viking of AI

Set of abstraction libraries to easily build Text and Audio based bots

This repository will guide you to create automatically generate YouTube Transcription using Using OpenAI's Whisper

Bot de conversão de áudio no whatsapp para texto

A platform to enhance medical e-Shadowing.

Freeswitch Speech-To-Text module

Speech-enabled Retrieval-Augmented Generation solution

Classical music exploration chatbot built using Embabel and Neo4j

Talk to Rawan voice-to-voice using speech recognition or text-to-speech, with elevenlabs technology and chatgpt on the web.

CLI educacional para transcrição com OpenAI Whisper

ProjectBEA is a modular, autonomous AI VTuber engine. Features RAG memory, OBS integration, Discord voice calls, and an autonomous Minecraft agent. Built with Python/React, it supports swappable LLMs/TTS and a plugin-based skill system for easy extension.

OpenClaw skill: genpark voice shop

A collection of real-world use cases built with agentcall.dev — each folder is a self-contained, working example. By Pattern AI Labs.

29 controlled experiments on Nemotron 3 Ultra: what prompting can and cannot do to a frontier model. Voice 4/8 to 7/8, hidden bugs 1/5 to 5/5 — blind dual-judge graded, no fine-tuning.

Minimalistic dictation app for Mac. (OpenAI Whisper wrapper)

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、视觉与 HMI；LLM 只负责理解与规划，VAL 负责确定性安全执行。

The FULL-VOCAL interaction driven AI system that actively sustains your daily. Simply talk and everything is done.

鳳問 Ask Audrey — cited AI answers from Audrey Tang's 30-year transcript archive (archive.tw). Cloudflare Workers + Hono; web + LINE bot. 以 AI 檢索唐鳳逐字稿、附出處作答

Персональный ИИ-ассистент нового поколения для Windows — голос, зрение, управление ПК, навыки, память.

Control your live Kimi CLI sessions from your phone — self-hosted PWA over tmux: live chat, swarm progress, push notifications, voice input. Zero dependencies.

Create an AI by chatting - it gets a URL, a memory you can see, a body across your devices, a voice, and a wallet.

Simulación interactiva del HAL 9000 de 2001: Una Odisea del Espacio, con una interfaz inspirada en la nave Discovery One. Permite conversar con la icónica IA, recreando su personalidad serena pero inquietante para una experiencia inmersiva.

Voice-first language practice with Flutter, Go, OpenAI Realtime, Firebase, and Cloud Run.

real-time ai voice assistant with animated orb ui powered by anthropic claude

This project is made for a hackathon and is named **AgentOps**. It is a platform where business owners can integrate automation into their websites to automate repetitive tasks like proposal generation and invoice generation, ensuring they never miss a client.

Discord AI bot capable of chatting and moderating, trained on conversation transcripts of Elon Musk

🤖 Computer Autopilot - AI-powered Windows automation using natural language. A modern Windows automation tool that lets you control your computer through natural language commands. Features a sleek GUI with chat interface, voice control, and RPA capabilities. Powered by LLMs for intelligent UI interaction and task automation.

AI Voice Agents: Exploring the Next Generation of Human-Machine Interaction! 🎙️🤖🎧

Eva the AI assistant

end-to-end voicebot that answers open domain questions.