FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates

MindSpider：专为舆情分析设计的AI爬虫

从0实现一个简洁清晰的Deep Search Agent

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

open-vocabulary sound event detection

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

SoulX Podcast TTS Metal Test

[ACM MM 2025] AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation

A Python Library for Full Reference Binaural Fidelity Testing, Visualization & Feature Generation

Official Repository for "Efficient Vocal Source Separation Through Windowed RoFormer"

The code of QaSNet

Official implementation of Decoupled MeanFlow

SAM 2++: Tracking Anything at Any Granularity

Transcription, forced alignment, and audio indexing with OpenAI's Whisper

[INTERSPEECH 2025 Oral]Official code for "Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment"

"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

Official Repository of UltraVoice

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

Code for the blog "Neural audio codecs: how to get audio into LLMs"

Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark

An interface library for RL post training with environments.

An easy-to-use, fast, and easily integrable tool for evaluating audio LLM

PyTorch-native post-training at scale

中国市场分析脚本是一个功能强大的Python工具，旨在为用户提供对中国A股市场的深入分析。该脚本利用Akshare库从多种数据源获取实时和历史股票数据，并计算关键财务指标，以帮助投资者做出明智的决策。

OpenAI compatible TTS for Sesame CSM:1b & dia:1.6b - Voice Cloning from File/YT

Vogent Turn: fast, open-source turn-detection for Voice AI applications