🍌 8000+ selected Nano Banana Pro prompts with images, multilingual support, and instant gallery preview. Open-source prompt engineering library

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

DigitalPlat FreeDomain: Free Domain For Everyone

ONNX Inference of Pyannote Segmentation

A python API for reading and writing SOFA files (https://www.sofaconventions.org/)

SOFA Toolbox (API for Matlab, Octave)

A Python library aimed at acousticians.

官方推荐的 ChatTTS 资源汇总项目，整理了全网相关资源和常见问题 || Officially recommended ChatTTS resource collection project

Official repository of the work "Speaker Distance Estimation in Enclosures from Single-Channel Audio" published to IEEE/ACM Transactions on Audio, Speech, and Language Processing.

This is the official implementation of reverberant speech to room impulse response estimator

Open-Source Frontier Voice AI

Code for the paper "RIR-in-a-Box : Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation" presented at Interspeech 2024.

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

Model for selecting perceptually relevant early reflections for parametric spatial sound rendering

Impulse response generation based on state-of-the-art geometric sound propagation engine.

SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

A collection of projects showcasing RAG, agents, workflows, and other AI use cases

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Production-ready platform for agentic workflow development.

实时STT，连接OpenAI接口/智谱AI（流式LLM）和GPT-SOVITS/Edge-TTS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果

TTS with kokoro and onnx runtime

SuperSonic is the next-generation AI+BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.

Self-hosted voice chat with LLMs

The reproduced code for Google's SoundStorm

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

A high-throughput and memory-efficient inference and serving engine for LLMs

🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot …

The official implementation of GTCRN, an ultra-lightweight SE model.

Efficient Multimodal Large Language Models: A Survey