Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Merriam-Webster' dictionary extension for Chrome and any chromium based browser

MiMo-Audio: Audio Language Models are Few-Shot Learners

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言，同时支持语音识别转录、语音合成、字幕翻译。

A collection of Flutter examples and demos

A showcase app for the Flutter SDK. Wonderous will educate and entertain as you uncover information about some of the most famous structures in the world.

Drift is an easy to use, reactive, typesafe persistence library for Dart & Flutter.

Extremely fast, easy to use, and fully async NoSQL database for Flutter

Autonomous agents for everyone

仙三开源版 - The efforts to create an open-source implementation of Chinese Paladin 3

A tool to practice English speaking

This tool uses AI to evaluate your pronunciation.

Extract phoneme-level timestamps from speeh audio.

通过修改Hosts解决国内Github经常抽风访问不到,每日更新

💖🧸 Self hosted, you owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

Frontier Open-Source Text-to-Speech

GSAP (GreenSock Animation Platform), a JavaScript animation library for the modern web

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Kernels & AI inference engine for phone chips

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

An open-source AI agent that brings the power of Gemini directly into your terminal.

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

SoTA open-source TTS

基于Deeplx和Playwright提供的简单易用，快速，免费，不限制文件大小，支持超长文本翻译，跨平台的文件翻译工具 / Easy-to-use, fast, free, unlimited file size and cross platform file translation tool based on Deeplx & Playwright that supports long …

Uncomplicated Observability for Python and beyond! 🪵🔥