Starred repositories
Curated list of design and UI resources from stock photos, web templates, CSS frameworks, UI libraries, tools and much more
Training code for FAcodec presented in NaturalSpeech3
Unsupervised Speech Decomposition Via Triple Information Bottleneck
Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications
Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines
A lightweight text-to-speech model with zero-shot voice cloning
Conversion between Traditional and Simplified Chinese
A highly compressive and high-quality neural audio codec for speech models.
Hono <-> React Router Adapter
Scalar is an open-source API platform: 🌐 Modern Rest API Client 📖 Beautiful API References …
Node.js implementation of Web audio API
Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.
Official home of the DB Browser for SQLite (DB4S) project. Previously known as "SQLite Database Browser" and "Database Browser for SQLite". Website at:
A phone number can reveal whether a device is active, in standby or offline (and more). This PoC demonstrates how delivery receipts + RTT timing leak sensitive device-activity patterns. (WhatsApp /…
A gRPC client library for Firestore, intended to run on Cloud Run.
Kanade is a speech tokenizer that encodes speech into compact content tokens and global embeddings and decodes them back to mel spectrograms.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
A native macOS menu bar app for managing audio device priorities
Node.js port of voicepeaky with enhanced narrator/emotion support and concurrent processing
Official Repository of Smule Renaissance, Smule's Vocal Restoration Models
Fast and accurate fundamental frequency (F0) detector using convolutional neural networks
A reference implementation of the Resonate algorithm in C++ for Python.