Projects sharing features with LiveTalking

EMO is an AI portrait animator and audio-to-video diffusion model designed to generate expressive talking head videos. It transforms a single static portrait image and an audio track into a synchronized video of a person speaking. The system focuses on digital human synthesis, producing high-fidelity facial movements and emotional cues. It synchronizes lip movements and facial gestures to match spoken voice recordings to create realistic portrait animations. The framework utilizes a diffusion process and a cross-modal alignment mechanism to ensure timing between audio signals and visual land

MuseTalk is a deep learning lip synchronization system designed to align video facial movements with audio tracks for high-fidelity video dubbing. It functions as an engine that matches facial expressions to audio input in real-time, enabling the modification of a speaker's lip movements to match new audio sources across different languages. The project features a distributed GPU training pipeline and a multi-stage processing workflow for refining the visual accuracy of synthetic speech. It distinguishes itself through the use of region-specific face masking and mouth openness control, which

Video-retalking is an AI lip synchronization framework and talking head video editor designed to match the mouth movements of a subject in a video to a target audio track. It utilizes a deep learning pipeline to synchronize speech with video recordings. The system employs a two-stage generation process that separates coarse lip movement from high-resolution detail refinement. It incorporates identity-aware face refinement and expression template alignment to maintain photorealistic skin textures and ensure visual consistency across video frames. The toolset covers facial expression modificat

Wav2Lip is a deep learning lip sync model and neural talking head framework designed to synchronize the lip movements in a video to match a provided audio file. It functions as a computer vision lip synchronizer and speech-to-lip generator that maps speech patterns to visual mouth movements to produce realistic talking head videos. The system utilizes a framework for training and evaluating models that align audio and video frames. This includes the ability to train lip-sync models and visual discriminators using speech-to-lip datasets and evaluating the resulting synchronization accuracy thr

GLaDOS is a multimodal AI agent framework designed to create autonomous systems that process text, speech, and visual data to interact with users and their environment. It centers on an AI personality framework that emulates complex character personas using a multi-agent architecture and configurable behavioral profiles. The project distinguishes itself through an integrated tool layer that connects language models to external hardware, smart home devices, and system APIs via a standardized protocol. It features a character text-to-speech engine with low-latency playback and interruption hand

Duix-Avatar is an AI digital human toolkit used to create, clone, and animate realistic virtual personas. It functions as a digital persona cloning tool and a text-to-speech animation API that converts written text or audio into synthetic voice and facial motion markers. The framework provides an offline video generation engine that renders digital human animations and lip-synced videos on local hardware. It includes a specialized lip sync engine to synchronize mouth movements with audio waveforms and a pipeline for extracting facial and vocal features from source media to create synthetic re

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

InfiniteTalk is an open-source system for generating talking head videos driven by audio input. It synthesizes realistic lip movements, head poses, and facial expressions synchronized to a spoken audio track, using either a single still image or a small set of reference video frames as the visual source. The system can produce videos of arbitrary length while maintaining temporal coherence, and it supports animating multiple subjects in a single scene. A key differentiator is the ability to coordinate multiple talking subjects through a structured JSON description, giving each independent lip

AniPortrait is an AI video synthesis pipeline designed to generate photorealistic speaking portraits and facial animations. It functions as a talking head generator and audio-driven animator that synchronizes lip movements, expressions, and head poses to speech or reference video sources. The system includes a facial expression transfer tool for reenacting movements from a source video onto a static reference image. It utilizes a latent diffusion model with reference-based image conditioning to maintain visual identity and consistency across generated frames. The pipeline covers audio-to-exp

LongCat-Video is a collection of specialized models for video synthesis, featuring a large language model based architecture for creating high-resolution videos from text, images, or existing sequences. It includes dedicated systems for text-to-video generation, image-to-video animation, and the creation of talking avatars. The project provides specific capabilities for extending the length of existing clips through a video continuation model that predicts subsequent frames. It also enables the synchronization of character lip movements with audio and text prompts to produce speaking videos.

EasyVtuber is 2D avatar animation software that transforms a single static image into a real-time animated character. It functions as a face tracking animation tool and live streaming avatar driver, mapping facial movements from webcams or iOS devices to drive virtual expressions and head motion. The project distinguishes itself through a neural animation pipeline that includes AI video upscaling and frame interpolation to increase visual smoothness and resolution. It utilizes a transparent video streaming system via Spout2, allowing rendered frames with alpha channels to be sent directly to

Aigcpanel is a visual workflow automation tool and model lifecycle manager designed for generative AI media pipelines. It provides a unified interface to install, launch, and configure both local and remote AI model endpoints, acting as an orchestration platform for large language models and AI tools. The system features a drag-and-drop node editor for chaining AI models and scripts into automated processing pipelines. It distinguishes itself with a breakpoint-aware execution model that allows users to pause and resume long media tasks from specific points in the workflow. Additionally, it in

VDO.Ninja is a low-latency peer-to-peer media routing service and video streaming platform designed to integrate remote audio and video feeds into professional production workflows. It functions as a WebRTC broadcast integration tool and studio controller, allowing for the direct transmission of high-definition media between publishers and viewers with minimal delay. The platform distinguishes itself through extensive protocol bridging, converting between WebRTC, WHIP, WHEP, SRT, and RTMP to ensure compatibility across diverse network environments and professional studio software. It includes

This project serves as a curated directory and resource hub for developers working with generative artificial intelligence. It provides a comprehensive index of open-source software solutions, frameworks, and project examples designed to help users discover and implement advanced AI systems. The repository focuses on practical implementations of agentic, multimodal, and retrieval-augmented generation architectures. It highlights tools for building conversational assistants, voice-enabled agents, and automated workflows that leverage large language models. By showcasing diverse technical domai

LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it

SadTalker is an audio-driven talking head generator that produces synchronized speaking videos from a single source image and an input audio file. The system utilizes a deep learning framework to map speech signals to facial motion data, enabling the creation of lifelike digital avatars and animated characters. The project distinguishes itself by employing a three-dimensional morphable model to translate audio features into precise facial landmarks and head pose parameters. It integrates latent diffusion motion synthesis to generate naturalistic head movements and uses expression-aware textur

Ant-Media-Server is a server-side streaming engine designed for real-time audio and video broadcasting. It functions as a live media transcoder and WebRTC streaming server, facilitating the ingestion, processing, and delivery of media streams across multiple protocols. The platform is distinguished by its cloud-scale media infrastructure, which automates server capacity expansion to handle fluctuating volumes of concurrent viewers. It utilizes adaptive bitrate streaming to adjust video quality in real time based on network conditions and employs WebRTC and SRT to achieve ultra-low latency del

This project is an RTMP media streaming SDK and a real-time communication framework designed for pushing and playing audio and video streams. It provides tools for interactive broadcasting, low-latency voice and video calls, and a cross-platform media player compatible with Windows, iOS, and Android. The toolkit enables interactive live broadcasting with support for multi-host interactions and the ability to push streams to distribution servers via CDN. It includes a cloud recording manager for capturing live sessions and saving them as files to cloud storage, along with a system for composit

ChatTTS-ui is a web-based interface and API wrapper for the ChatTTS model, designed to convert written text and mixed language input into spoken audio. It functions as an AI speech synthesis dashboard and a programmatic generator for creating naturalistic voice output. The project focuses on custom voice profiling and speech nuance control. It allows for the maintenance of consistent speaker characteristics using seed values and data files, while providing controls for tone, laughter, and pauses through behavioral prompts and sampling parameters. The system includes a client-server architect

Vocode-python is an LLM voice AI framework and orchestration library used to build real-time conversational agents. It functions as a speech-to-speech pipeline that integrates large language models with speech-to-text and text-to-speech services to facilitate continuous spoken dialogue. The framework acts as a telephony integration gateway, connecting voice agents to phone lines and video conferencing platforms through automated calling infrastructure. It provides the means to deploy voice channels to external communication platforms and host telephony servers. The library manages the end-to

Project-Lightspeed is a low-latency video relay and WebRTC live streaming server. It functions as an OBS streaming backend that ingests media streams and converts them for real-time playback in web browsers. The system operates as a WebSocket stream orchestrator, managing connection handshakes and stream authentication to coordinate signaling between the server and the client browser. It utilizes a high-speed protocol to achieve sub-second delay between the broadcast source and the viewer. The server covers media relay capabilities, including network packet relaying and the ingestion of vide

🎤 微软语音合成工具，使用 Electron Vue ElementPlus Vite 构建。

FastRTC is a Python framework for building low-latency, bidirectional audio and video streams. It serves as a real-time communication library that provides a wrapper for WebRTC media servers, allowing users to create streaming applications with integrated media handling. The project distinguishes itself by providing a gateway for telephony integration, which maps temporary phone numbers to streaming media endpoints. It also includes built-in voice activity detection to manage automatic turn-taking and speech boundary identification in real-time conversations. The library supports mounting me

RealtimeVoiceChat is a conversational AI gateway and voice chat interface that enables real-time spoken interactions with large language models. It functions as a streaming audio pipeline that integrates speech-to-text transcription and text-to-speech synthesis to facilitate natural voice conversations. The system utilizes WebSocket-based audio streaming and an asynchronous text-to-speech pipeline to maintain low latency. It includes specialized conversational controls such as silence-based turn detection and client-side interrupt handling, which stops active audio playback when new user spee

This project is a real-time communication and media streaming server designed for broadcasting, recording, and distributing audio and video content. It functions as a live streaming server and an RTMP media server, providing the infrastructure necessary to deliver real-time media to multiple concurrent viewers over a network. The system distinguishes itself through a multi-protocol media gateway that supports RTMP, E-RTMP v2 for modern codecs like HEVC and AV1, and HTTP media tunneling to bypass restrictive firewalls. It further acts as a real-time communication platform by synchronizing shar

Personaplex is an LLM speech-to-speech framework and conversational AI persona engine designed for real-time voice interfaces. It provides a system for defining AI identities and vocal characteristics through a combination of text-based role prompts and audio reference files. The project features a real-time AI voice interface that supports full-duplex human-AI dialogue, enabling multiple parties to speak and listen simultaneously via bidirectional audio streaming. It includes a GPU-accelerated audio processor and a speech-to-speech pipeline to facilitate low-latency conversations. The frame