Voice Assistant Python Packages

pipecat-ai

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

agentscope

Build and run agents you can see, understand and trust.

ovos-spec-tools

Reference implementation of the OVOS formal specifications — sentence template expander, locale resource loader, dialog renderer, language matching, and a locale linter

hivemind-bus-client

Python client library for HiveMind — encrypted, routed bus client with WebSocket, HTTP, async, and MQTT transports (the library for building satellites)

thalovant

Python SDK for direct Thalovant HiveMind HTTP clients

dv-pipecat-ai

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

hivemind-core

Central HiveMind hub server: connects satellite devices and AI agents to an OVOS instance over an encrypted mesh protocol

thalovant-skillkit

Shared plumbing for the Thalovant OVOS skills

achatbot

An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.

personal-jarvis

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows, macOS, Linux.

gmlx

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

hivemind-voice-sat

OVOS voice satellite for HiveMind — full on-device voice stack (microphone, VAD, wake word, STT, TTS)

kenzy

Smart Ai Voice Assistant written in Python

easyspeak-linux

Voice control for Linux desktops. Fully local, no cloud, Wayland-native.

hivemind-voice-relay

HiveMind voice relay — local wake word, remote STT/TTS via the hivemind-audio-binary-protocol plugin

thalovant-skill-custos-fallback

Give unanswered requests a helpful reply instead of leaving the room silent.

superdialog

Low latency framework for realtime conversations.

hivemind-mic-satellite

Lightweight HiveMind microphone satellite — streams audio to the hive for server-side STT/TTS (ideal for low-power devices)

brok

it is an AI

beseda

Voice conversations with your coding agent in the terminal: wake word, local STT/TTS on macOS, English and Russian

attenlabs-saa

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

stark-engine

S.T.A.R.K. - Speech And Text Algorithmic Recognition Kit

pvrhino

On-device Speech-to-Intent engine powered by deep learning

autoyou-lite

Self-hosted AI server and agent framework. Pair your phone, browser or desktop with your own computer peer to peer over WebRTC, and run models, agents and web apps on hardware you control. Source-available.