voice-agent

Open repos and models their makers tagged voice-agent, most starred first. The same for everyone.

AI on my own machineRepo

VoiceMem

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

  • 2.9k
  • Python
  • Apache-2.0
  • 2 mo ago
xzf-thuTake it
AI on my own machineRepo

mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.

  • 2.5k
  • Zig
  • 12 h ago
ddalcuTake it
Voice and audioRepo

Patter

Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.

  • 1.1k
  • Python
  • MIT
  • 2 wk ago
PatterAITake it
Run my own servicesRepo

ai-native-callcenter

Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).

  • 689
  • Go
  • Apache-2.0
  • 11 h ago
rasonyangTake it
AI agentsRepo

Deuz-SDK

TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.

  • 508
  • TypeScript
  • MIT
  • 5 wk ago
Deuz-AITake it
Voice and audioRepo

esp32-thinks

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.

  • 258
  • Shell
  • MIT
  • 4 wk ago
raullenchaiTake it
AI agentsRepo

openclaw-whobot-skill

呼波特 WhoBot 官方 AI 电话数字员工 Skill:在 WorkBuddy / Claude Code / Codex / OpenClaw / Cursor 里挑选、体验、创建和调优会打真实电话的 AI 员工,上传线索外呼 | Official WhoBot agent skill for AI phone agents (voice agents)

  • 121
  • Python
  • MIT
  • 2 min ago
whobot-comTake it
Voice and audioRepo

speech-core

On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.

  • 101
  • C++
  • Apache-2.0
  • 9 d ago
soniqoTake it
Voice and audioRepo

OpenVoiceUI

Voice-powered AI assistant platform — connect any LLM, any TTS, with a live web canvas, music generation, and agent orchestration using openclaw. Install: npx openvoiceui setup

  • 86
  • Python
  • MIT
  • 17 min ago
MCERQUATake it
AI on my own machineRepo

siphon

The open-source foundation for production Voice AI. Build, scale, and own your AI calling infrastructure. Bridge legacy SIP to modern LLMs over ultra-low latency WebRTC pipelines. Zero platform fees, BYOK, and full data sovereignty.

  • 63
  • Python
  • Apache-2.0
  • 6 mo ago
AI on my own machineRepo

expo-thinking-orbs

AI thinking indicators and a voice-agent orb for React Native and Expo. Six dotted loading animations plus an audio-reactive voice orb, on the UI thread with Skia + Reanimated. Port of Jakub Antalik's thinking-orbs.

  • 42
  • TypeScript
  • MIT
  • 3 mo ago
Run my own servicesRepo

bageo-call

AI phone assistant for your real phone number: Gemini Live answers and makes calls through a spare rooted Android phone (Pixel) with your own SIM. Call screening, spam/scam call stalling, transcripts, summaries. Self-hosted, open source. 八哥 AI 接電話/代打電話

  • 35
  • Rust
  • AGPL-3.0
  • 3 h ago
h4lo-voidTake it
Search GitHub and Hugging Face for voice-agent

Get , open it once and sign in. Then come back here and press the button again.