An interface library for RL post training with environments.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

JATTS: A modern, research-oriented Japanese Text-to-speech Open-sourced Toolkit

A Datacenter Scale Distributed Inference Serving Framework

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

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

SGLang is a high-performance serving framework for large language models and multimodal models.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

pyopenjtalk-plus: A Python wrapper for OpenJTalk with additional improvements

[ICASSP 2024] TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"

Maestro: Netflix’s Workflow Orchestrator

Controllable and fast Text-to-Speech for over 7000 languages!

Inference and training library for high-quality TTS models.

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

A PyTorch-based Speech Toolkit

The Nendo AI Audio Tool Suite

Nendo is an open source platform for AI-driven audio management, intelligence, and generation.

Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain

🔊 Text-Prompted Generative Audio Model

青空文庫振り仮名注釈付き音声コーパスのデータセット

Foundational model for human-like, expressive TTS

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.