#voice-assistant

Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and call screening

Cross-platform AI companion port of OpenClicky for Windows, Linux, and macOS.

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.

Voice AI agent that lets Romanians handle civic tasks by phone — pay taxes, file city reports, understand bureaucratic letters. One phone number, plain Romanian, any phone.

Professional-grade real-time AI Voice Assistant platform built with FastAPI, Next.js, and VAPI for intelligent voice call orchestration.

Give your AI agent a talking, lip-syncing face — 12-emotion particle face, in-browser Whisper (WebGPU), bring-your-own-agent bridge. MIT.

Native macOS floating voice assistant with a glass companion UI, powered by logged-in Codex or Claude CLI accounts.

Voice-enabled personal assistant for Hermes Agent. Open mic with wake word, fully local — no API keys, no accounts, 35 languages.

Jarvis 2.0 — Personal AI Voice Assistant for macOS with local Whisper STT, Claude Haiku LLM, and 3 isolated microservices. Production-ready.

A voice agent rendered as a potato — rude, russet, and driven by a live OpenAI Realtime call. Remembers what you tell it, and hands work to Claude Code, Codex, OpenCode or Grok Build.

White-label multi-workspace support chatbot with self-hosted voice: talk to your bot, hear it answer — Next.js 15 + local RAG (sqlite-vec) + faster-whisper STT + Kokoro/Coqui TTS, multi-language

Intelligent research agent - searches 250M+ academic papers, generates AI summaries with LLaMA 3.3 70B, exports PDF reports, and supports voice commands.

Voice-driven local Codex assistant for CachyOS and Omarchy, with Whisper transcription, Piper TTS, Hyprland hotkey integration, and persistent memory.

An open-source AI workflow platform for speech transcription, LLM-powered processing, and interactive transcript chat using any OpenAI-compatible API.

Local voice assistant for macOS Apple Silicon — wake-word → on-device STT → Claude → natural TTS, with speaker ID and DE/FR/EN.

A full-stack web-based voice assistant built with Python and Flask. Integrates OpenAI's GPT for intelligent conversational responses and IBM Watson Speech Libraries for Embed for seamless speech-to-text (STT) and text-to-speech (TTS) processing.

Real-time local voice agent (Jarvis-style) with instant barge-in, streaming STT/LLM/TTS, and pluggable AWS Bedrock/Ollama/OpenAI backends

Talk to your Claude Code sessions by voice, hands-free, from your phone

Local-first voice + gesture AI presence for macOS. Wake word → Whisper → three-tier router → Claude Agent SDK + MCP, behind a kill switch, device-scoped allowlist, voiceprint-gated confirmation and a full action log.

Axel — a self-hosted, voice-driven AI coding agent for your dev environment

Local voice agent (eng) with barge-in. Three layer memory, browser as mic over LAN, ~1.9 s to first audio on a 4070 Super

Voice assistant for Windows powered by Claude Code — wake word, GPU STT, intent routing, streaming TTS, safety-confirmation hook.

Voice-activated personal AI assistant for macOS. The Siri/Alexa replacement that uses your existing Claude/ChatGPT/Gemini Pro subscriptions — no API key, no per-token bills.

Interactive voice-controlled storyteller for Raspberry Pi (ReSpeaker) or PC: OpenAI STT/LLM/TTS, RAG worlds, substory dramaturgy, moderation, de/en, web admin.

Yandex.Alisa skill — a wise-elk persona backed by an OpenAI-compatible LLM router, with multi-turn memory and a slow-LLM keep-alive pattern