MyCroft
summary
An open source voice assistant written in Python that runs on Raspberry Pi and desktop Linux, Mycroft uses WebSockets for a message bus, PocketSphinx for offline wake‑word detection, cloud speech‑to‑text by default (local STT configurable), and Mimic for TTS; skills are Python files with vocabulary, code and dialogue and execute locally; a Mark 1 Kickstarter device ships (started shipping about two weeks ago) and community GNOME/KDE/Chrome integrations already work.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:07Problems with IoT
- 3:39Voice as IoT interface
- 5:03Why Mycroft
- 10:26Community skills demo
- 12:57Mycroft core technology
- 15:32Installing Mycroft
- 18:26GNOME shell extension
- 20:16Skill structure
- 24:22Building your own skills
- 25:24How to contribute
- 26:29Q&A
related talks
43mAnatomy of an open source voice assistant
41m"Hey Mycroft": Getting Started with the OSS Home Assistant
45mComparison of Voice Assistant SDKs for Embedded Linux Devices
34mVoice-Controlled Lights on a Raspberry Pi
37mVoice-controlled Home Automation from Scratch Using IBM Watson, Docker, IFTTT, and Serverless
30mMindmeld: An Open-source, Deep-domain Conversational AI Toolkit
51mBuilding an AI assistant that makes phone calls
44mSmartly AI: Cross Platform Voice Application Creation