A framework for efficient model inference with omni-modality models

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, iFlow as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5, Claude, Qwe…

Sub2API-CRS2 一站式开源中转服务，让 Claude、Openai 、Gemini、Antigravity订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

Scalable data pre processing and curation toolkit for LLMs

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…

Generative models for conditional audio generation

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Open-Source Frontier Voice AI

The best ChatGPT that $100 can buy.

Idea2Paper Offical Demo

Official inference repo for FLUX.2 models

5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs

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

Official implementation of "Continuous Autoregressive Language Models"

Trainging, inference, and testing of the SAC speech codec model.

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Official Implementation of Paper Transfer between Modalities with MetaQueries

A toolkit for processing speech data and creating speech datasets

Official inference repo for FLUX.1 models