Audio agents

Agentic voice AI using ConversationRelay. 5 minute setup.

The GoLang Fullstack LLM Framework(llm intergration、cache、route、rag、ai agent、program、engine app、optimizer、speech)

This custom component for Home Assistant allows you to generate text responses using GigaChain LLM framework (like GigaChat, YandexGPT, ChatGPT).

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

Headless Matrix WebRTC voice AND video agent — auto-answers calls, bridges audio to any AI agent via PipeWire, optional camera-frame vision for multimodal LLMs

Native AI workspace for macOS. Local and hosted models, agents, browser, terminal, voice, and mobile access. Locus is wallet-free; LocusX adds wallets.

Chatbot Flutter App used to track inventory of product and description using Dialogflow

Use "cw" in the CLI. No instructions necessary, just hit <enter>. Can also be used as a library. Commit Whisperer is an AI genius for generating meaningful git commit messages from repository state and user instructions.

🤖 AI Conversation Agent for Home Assistant. Compatible with any OpenAI format LLM providers, supports STT/TTS

Open source voice bot for Humanoid Robots and virtual digital humans

A spoken English education chatbot based on ChatGPT/whsiper and gTTS.社恐人士的英语角

React/Next.js visual dashboard for the OpenClaw AI gateway — every CLI command as a UI page, with speech-to-text everywhere

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

An ASP.NET Core web application for conducting AI-powered mock technical interviews. Candidates take text or voice-style interviews on configurable topics and subtopics; the app uses an AI agent (OpenAI) to ask questions, adapt difficulty, and produce scored evaluations with feedback.

Demos of Whisper model's functionality in Gradio-powered minimalistic Web apps: offline, using Azure OpenAI and Azure AI Speech.

[DEPRECEATED] A miniature replica of OpenAI's MuseNet

NOVA is a customizable voice assistant made with Python.

Blabber — 首个 Agentic 播客视频生成平台。一句提示词，生成一整期动画播客节目：AI 编写对白 · 双主持配音 · 逐帧口型同步 · 自动运镜剪辑，从想法到成片一站直达。Blabber — The first agentic podcast video generation platform. One prompt, a full animated podcast show: AI-written dialogue · dual-host voices · frame-accurate lip sync · automated camera direction & editing, from idea to final cut.

Welcome to LLM-Utility-Cookbook! Here you'll find tools to make LLMs easy: voice to text, text to voice, document scan to text, prompt management, and more. Jump in, make your work easier

Telegram bot with options to receive text and response with ChatGPT and also parse voice and response in the same language.

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

Java Application for local area network Voice Chat

Freeswitch Speech-To-Text module

Whisper in TensorRT-LLM

GPT Table Semantic Parsing with complex & non-intuitive structure.

Real-time conversation assistant with dual audio transcription and GPT-powered responses, perfect for meetings and interviews.

A simple Python based implementation of a Raspberry Pi based, OpenAI ChatGPT enabled voice assistant

This is speech to speech(voice chat) applications. Between of user and AI

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.

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

Local-first digital persona engine with long-term memory, voice, and channel integrations

Freeswitch Speech-To-Text module

Voice Agent implementations for the VAmoS Benchmark

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

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extension.

Logic-based multi-LLM voice router for Home Assistant, combining native intents, local Qwen, GPU-aware desktop Ollama, and cloud AI with intelligent fallback.

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).

Local, voice-enabled AI assistant on the terminal

Conversation support for Home Assistant using HuggingChat.

AI-Powered Text-To-Speech Video Generator This web application uses AI to generate captivating and informative video scripts based on user inputs. It is still under development, but it has the potential to be a useful tool.

A chatbox application built using Nuxt 3 powered by Open AI Text completion endpoint. You can select different personality of your AI friend. The default will respond in Japanese. You can use this app to practice your Nihongo skills!

Generate videos on any topic automatically, harnessing OpenAI for script generation, ElevenLabs for TTS, and Giphy and Unsplash for multimedia

format whisper transcripts to .srt

:shipit: Adds realtime chat for ChatGPT Voice Mode [Unofficial]

Smart assistant in Telegram bot format for transcribing online meetings

Your personal voice language teacher based on ChatGPT + Whisper + Eleven Labs

Create subtitles for your video and traduction in a few clicks with ai

It is a voice bot based on LLM.

This is a fully local AI Assistant that uses Silero VAD, Faster-Whisper, LM Studio, Coqui TTS, MiniLM-L6-v2 and ChromaDB

Voice & Vision Assistant for the Blind is an AI-powered assistant that helps blind and low-vision users navigate the world more independently. It uses real-time vision, speech recognition, and natural language understanding to describe surroundings, identify people or objects, and answer spoken questions instantly.

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

Simple and easy to use desktop application for ChatGPT & AI, will supporting Window, MacOS, Linux platforms. | 洁且易用的 ChatGPT/星火大模型 & AI 的跨平台客户端

Instantly generate and download your PPT by simply uploading your audio file and letting our AI do the work!

God-GPT: a PoC of a godlike autonomous agent that leverages the Dalee-2 and whisper.cpp

Google Alexa like Laptop assistant written in Python which uses google's speech-to-text library to process voice input.

Flexiee is a customizable Python voice assistant that understands spoken commands, performs useful tasks,

A web application that utilizes AI to help you improve your English speaking and conversation skills.

Empower your wearable tech with AI. WearAI integrates OpenAI's ChatGPT with your smartwatch, enabling real-time voice-to-text and text-to-voice AI interactions on the go.

DesktopClaw is a state-aware desktop pet interface for your OpenClaw instance. It brings your AI to life as a reactive companion you can interact with via voice or text, while providing real-time session visibility, task feedback, and quick action triggers through a persistent, animated desktop presence.

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

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

transformers gguf mistral quantized 2-bit 3-bit

Your own voice + text AI assistant, embedded with one script tag, running 100% in the visitor's browser.

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

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

OpenWand - A LLM chat interface optimized for AI co-work for your desktop. Press a key, pick an intent, and OpenWand reads the right context, then streams an answer without making you leave what you're doing. Local-first, voice in/out, bring your own model provider.

长任务，不刷屏：关键进度清晰可见，完成后自动折叠，详情随时展开。 Long agent tasks, without transcript clutter: focused progress, auto-folded history, details on demand.

An advanced embodied AI agent with personality-driven interactions, multi-modal perception (vision, speech), autonomous task execution, and real-time voice synthesis. Inspired by robotics subsumption architectures, it bridges cognitive reasoning, behavioral decision-making, and virtual/physical body control for immersive AI experiences.

🎤 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:

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

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.

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.

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.

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.

🎙️🧠 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

Everyone deserves a chief of staff - your personal jarvis | not a chatbot. not another ai agent. | beta

Open-source AI video platform for education. Type a topic, and SARAS writes the script, narrates it, generates the visuals, and hands back a finished, captioned lesson video — in your language, in minutes.

长任务，不刷屏：关键进度清晰可见，完成后自动折叠，详情随时展开。 Long agent tasks, without transcript clutter: focused progress, auto-folded history, details on demand.

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

This repository contains my Bachelor's degree final year project. It is a Google colab based interactive Virtual Assistant built using open-sourced libraries.

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

🤖 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.

Penglai 蓬莱 — a local-first desktop distribution and composable plugin ecosystem for DeepSeek Harness

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

Terminal AI Agent with desktop pet Arona — eye-tracking pupils, voice cloning, Computer Use, TTS/STT, MCP. Built on Pi SDK. TypeScript + Python + Electron.

ClawCall：面向 OpenClaw 的 AI 外呼、智能外呼与电话机器人 Skill，支持中文通话、呼入接待、转写和通话记录；执行时支持中国大陆手机号。

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

Your personalized museum tour guide!