Haru: a low-latency, multilingual, full-duplex spoken dialogue model
Central telefônica open source operada por agentes de IA. Atende, executa ferramentas durante a ligação, consulta um humano e segue trabalhando depois que a chamada termina. Self-hosted.
System-One-controlled full-duplex voice interaction: turn-taking as plain-language decisions judged by Jev.
Talk to a Hermes Agent profile through Home Assistant Assist
Open full-duplex voice models that hear your tone and speak with one. One GPU with vLLM-Omni, or fully offline on a Mac with MLX. Zero-shot voice cloning, OpenAI Realtime / GPT-Live compatible, free hosted API trial. Apache-2.0.
OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain.
A Windows desktop voice agent with real-time conversation, a Live2D avatar, and background tasks for files, Office documents, and the web.
Run voice AI locally with open-source models. Bring it to any device with one command.
联想 ThinkSmart View(CD-18781Y)语音助手系统镜像:基于 rickx/ubuntu-thinksmart,开机直接进语音界面;含中英文刷机教程(写给人和 AI 助手)、出镜像脚本和设备修复服务|Voice-assistant system image for Lenovo ThinkSmart View (CD-18781Y), based on rickx/ubuntu-thinksmart: boots straight into the voice UI; flashing guide in Chinese and English (for people and AI agents), image build scripts and device fixes
Self-hosted voice AI agents with a Vapi-compatible API. AI phone agents on Twilio, Telnyx, Plivo, Vonage or SIP, with your keys or 100% local and free (Whisper, Ollama, Kokoro). No per-minute platform fee. npx openring
Demo implementation of the Real-time Context Standard
0 成本让 AI 给你打电话📞:iOS 原生通话,无需 Mac/开发者账号,无需购买或编写 App。Zero-cost AI phone calls over free SIP.
面向 M5Stack StackChan 的开源 AI 语音陪伴机器人固件,基于 ESP-IDF、PocketJS MicroTS 与 Rust。
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
Live WhatsApp voice calls with Hermes: call your bot, or let Hermes call you. Hermes plugin + whatsapp-rust sidecar + Gemini Live.
宗主:Waveshare 1.75C 圆屏 ESP32 上的 Grok Bot 语音终端,会眨眼的眼睛表情、字幕与朗读,含固件和后端源码(2.5.2.9)
The harness Mutuals uses to give life to its characters
Sonia - Local Voice Assistant in less than 13GB of RAM, TTS/STT, No Dedicated GPU required, Skills supported
A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.