69,259 visible repositories in the index
73–96 of 105 · Most stars
Translated🏠 Turn the Xiaoai speaker into a true AI smart butler: Xiaoai speaker + Xiaozhi + Hermes Agent + Home Assistant, with one Xiao Qi managing all whole-home devices such as Mijia and Haier. Control and query appliances by voice, scheduled tasks run on time, teach scenes and automations with a single sentence, proactive announcements and water leak alarms, all without opening an app or writing automations.
Powerful, free, context-aware AI native meeting assistant that transcribes in real-time and locally on your computer, writes the minutes, and lets your AI agent drive it.
Start recording when the user speaks
Sophon-Realtime v1.1: open full-duplex voice models that hear your tone and speak with one. Zero-shot voice cloning, one GPU with vLLM-Omni, OpenAI Realtime / GPT-Live compatible. Apache-2.0.
Text-to-Speech in JavaScript
An ESP32 board as the radio speaks Nintendo Switch local wireless (LDN/Pia) to Pokémon games on a real Switch: trades and Mystery Gift with FRLG, LGPE, SwSh, BDSP, PLA, SV and PLZA, from the desktop app, Android (USB) or iPhone (Bluetooth).
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
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.
A Rust JSON5 serializer and deserializer which speaks Serde.
TranslatedDSH plugin: makes her speak up on her own when no one is talking to her (rolls a die locally, and if the roll hits, DSH takes a turn of its own)
Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source.
In-memory key-value server in Rust that speaks RESP, so redis-cli and Redis clients connect. Locks, rate limits, job queues and a change feed are single commands; Raft-based failover. Clients for Rust, .NET, Go, Java, Python and Node.js.
Philips Hue nodes for Node-RED to control bridges, lights, groups, scenes, rules, automations, switches, dials, buttons, doorbells, speakers, motion & contact sensors, cameras, temperature & light level sensors and the Hue Play HDMI Sync Box — CLIP/v2 API, Hue Bridge Pro & MotionAware support.
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
Ruby wrapper for ‘espeak’ and ‘lame’ with sugar on top to create Text-To-Speech mp3 files.
A cross-platform modding language for GameMaker games. // Moved to Codeberg! https://codeberg.org/katsaii/catspeak-lang
:speaker: Simple examples to demonstrate various aspects of the Web Audio API.
Agent-ready video dubbing toolkit for Apple Silicon: local Chinese speech and bilingual subtitles. Single-speaker preview; human review required.
:speaker: Sonos mqtt controller. Control your speakers from your mqtt server. mqtt-smarthome insprired.
Middleware based authorization for Absinthe GraphQL powered by Bodyguard
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.
Music theory engine for embedded systems. Build musical instruments and controllers that interact with people and speak MIDI 1.0 and 2.0.
Multi-Room Audio based on Airplay/Airtunes with MQTT support :speaker:
A Löve light/shadow library