SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Multilingual Document Layout Parsing in a Single Vision-Language Model

A powerful framework for building realtime voice AI agents 🤖🎙️📹

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

Production First and Production Ready End-to-End Speech Recognition Toolkit

real time face swap and one-click video deepfake with only a single image

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Towards Human-Sounding Speech

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Spark-TTS Inference Code

Effortless Real-Time Sign Language Translation

This project is to train an RWKV LLM for TTS generation which compatible to other TTS engine(like fish/cosy/chattts).

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

Brand new TTS solution

A fast multimodal LLM for real-time voice

Local realtime voice AI

Multilingual Voice Understanding Model