This project provides a production-ready, real-time inference server for LatentSync, enabling high-quality, low-latency 2D digital human live streaming. It features a robust multi-process architecture, seamless idle/formal stream switching with smooth crossfade transitions, and is optimized for real-world deployment scenarios.
☆31Aug 16, 2025Updated last year
Alternatives and similar repositories for LatentsyncRealtime
Users that are interested in LatentsyncRealtime are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 关键词唤醒（KWS）、活跃说话检测（VAD）、 语音到文字转录（STT）、文字到语音转录（TTS）、说话人ID (speaker_id),其中KWS、speaker_id、speaker_diarization支持瑞芯微NPU推理☆12Feb 29, 2024Updated 2 years ago
- 使用OpenCV部署图像描述Image_Captioning，包含C++和Python两个版本的程序☆12Dec 22, 2023Updated 2 years ago
- ☆19Mar 11, 2026Updated 7 months ago
- Independent Gradio UI and workflow layer for self-hosted HeyGem-compatible digital-human services.☆39Aug 10, 2026Updated 2 months ago
- Generate ARKit expression from audio in realtime☆231Oct 24, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 使用ONNXRuntime部署Detic检测2万1千种类别的物体，包含C++和Python两个版本的程序☆17Aug 29, 2023Updated 3 years ago
- Ollama 0.12.3 + ROCm 7.1 for AMD MI50 (gfx906) Docker image☆11Apr 9, 2026Updated 6 months ago
- ☆13Jan 14, 2025Updated last year
- a repo to study TensorRT Plugin☆11Apr 30, 2025Updated last year
- FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution (Accepted at ACM Multimedia System Conference 2026)☆15Apr 20, 2026Updated 6 months ago
- 基于MuseTalk项目的实时数字人☆16Aug 16, 2025Updated last year
- ☆14Apr 28, 2023Updated 3 years ago
- 使用ONNXRuntime部署DeDoDe："局部特征匹配：检测，不要描述——描述，不要检测"。依然是C++和Python两个版本的程序☆23Dec 22, 2023Updated 2 years ago
- Cascaded Temporal Updating Network for Efficient Video Super-Resolution☆18Mar 4, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 为OP(operator & open)是一个开源插件(类似大漠插件)生成调用op_c_api.dll桥接代码☆22Jul 14, 2026Updated 3 months ago
- PiperTTS Enhanced with Lightweight Context-Aware Phonemizer☆16Sep 13, 2026Updated last month
- Java Bindings for the C++ library DeepSpeech☆10Jun 4, 2020Updated 6 years ago
- Goodness of Pronunciation Pipelines for OOV Removal☆10Jan 1, 2023Updated 3 years ago
- ☆14Nov 25, 2025Updated 11 months ago
- Perform the forced decoding with target transcription☆11Sep 12, 2018Updated 8 years ago
- This is application for dysarthria to improve their pronunciation by using deep learning☆10Dec 29, 2020Updated 5 years ago
- A one-page WebUI integrating VITS inference, training, and output in Sherpa-Onnx format.☆15Feb 2, 2025Updated last year
- phonetic similarity algorithms☆13Jun 19, 2018Updated 8 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs.…☆11Feb 4, 2020Updated 6 years ago
- 使用onnxruntime部署实时视频帧插值，包含C++和Python两个版本的程序☆29Feb 14, 2024Updated 2 years ago
- Real-time, low-latency AEC at 48 kHz — designed for efficiency and low CPU usage.☆14Jul 28, 2026Updated 3 months ago
- Next.js template showing Better Auth integration with WeChat / Weixin OAuth 2.0 login☆19Sep 27, 2025Updated last year
- A low cost tts system☆11Jul 7, 2025Updated last year
- ☆53Jan 20, 2025Updated last year
- Analytical methods for efficient inference of integrate-and-fire circuit models from single-trial spike trains☆11Oct 30, 2019Updated 7 years ago
- 洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频☆173Oct 20, 2024Updated 2 years ago
- A simple script to prepare dataset for training with TTS Tortoise model via https://git.ecker.tech/mrq/ai-voice-cloning☆13Jan 12, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- This project provides a Flask-based API for generating high-quality text-to-speech (TTS) audio using F5-TTS, a flexible and powerful TTS …☆16Updated this week
- ☆13Apr 9, 2021Updated 5 years ago
- An out-of-the-box animation visualization editor ｜ 一款开箱即用的动画可视化编辑器☆23May 12, 2025Updated last year
- Speech Processing & Linguistic Analysis Tool☆11Jun 30, 2019Updated 7 years ago
- mobile part of the open SSI framework☆12Sep 5, 2018Updated 8 years ago
- Keyword Spotting (KWS) API wrapper for TFLite streaming models.☆12Jul 28, 2021Updated 5 years ago
- Speech recognition module for Python, supporting several engines and APIs, online and offline.☆13Mar 9, 2022Updated 4 years ago