Long-form streaming TTS system for multi-speaker dialogue generation

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

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

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

MagicData-RAMC Dataset and Baseline

NeurIPS2023 - A generic biosignal learning framework. Large EEG pre-trained models.

Mother of All BCI Benchmarks

Official codebase for "Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking" (NeurIPS 2024, Spotlight).

[ICLR 2025] CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

[ICLR 2024 spotlight] Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI

Deep learning software to decode EEG, ECG or MEG signals

Public repository of the start kit

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

喜马拉雅专辑批量下载小工具

Frontier Open-Source Text-to-Speech

💯2025年 软件设计师 （软考中级）备考资源库+配套免费刷题软件。https://ruankaodaren.com

Simple software for downloading podcasts

xiaoyuzhou fm audio downloder.

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

🧡 Everything is RSSible

采集Apple Podcast数据

下载指定 B 站 UP 主全部或指定范围的音频，支持多种合集。A script to download all audios of the Bilibili uploader you love.

A feature-rich command-line audio/video downloader

👾 Fast and simple video download library and CLI tool written in Go

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

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

A generative speech model for daily dialogue.

Text-audio foundation model from Boson AI