video-localization

Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。

小牛视频翻译 是一款支持本地视频翻译、字幕翻译和 YouTube 视频翻译下载的 AI 工具，集成自动语音识别与多语言翻译功能，助力创作者高效完成视频翻译，应用于视频本地化与视频出海场景。

[NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering

VividDub — 公开视频语音翻译产品站；支持配音、字幕、本地化与硬字幕移除

YouTube to Bilibili video repurposing with bilingual subtitles

Unified Audio-Visual Perception for Multi-Task Video Localization

Local-first AI video dubbing with Whisper/WhisperX, Google translation, VoxCPM2 voice cloning, and optional LatentSync lip-sync.

Open Source Video Localization Pipeline

Free AI-powered tool to remove text from video online. Automatically eliminate subtitles, captions, text overlays, and text watermarks from videos. Fast, secure, and maintains HD quality. Perfect for content creators, editors, and marketers. No software installation needed.

A PyTorch implementation of RSC based on MMM 2023 paper "Weakly-supervised Temporal Action Localization with Regional Similarity Consistency"

A PyTorch implementation of MCA based on PRICAI 2022 paper "Weakly-supervised Temporal Action Localization with Multi-head Cross-modal Attention"

声帆 视频翻译｜AI 视频翻译、多语言配音、字幕翻译、声音克隆与口型同步

AI Tłumacz napisów to inteligentne narzędzie do tłumaczenia dialogów z plików .ass. Rozpoznaje płeć mówcy na podstawie analizy audio i automatycznie dostosowuje zaimki w języku polskim.zapewniając naturalne i precyzyjne tłumaczenie

Open-source Armenian video dubbing pipeline with ASR, translation, voice cloning, lip-sync, and emotion-aware TTS

Private, resumable Windows desktop workflow for downloading and localizing authorized videos with offline AI subtitles.

Official plugin for OrcaDub — AI video dubbing (bundles the @orcadub/mcp server + dub skill)

AI-powered Bengali SRT subtitle optimizer. High-precision spelling, phonetic, and contextual correction with 100% timestamp integrity.

Cinema-grade AI dubbing into 201 languages — keep every actor's real voice. Plus voice cloning, video, music & image. One platform by amaimedia.

Vendor-agnostic AI-assisted content workflow and operational checklists.

Curated open-source tools and agent skills for storytelling, learning videos, UGC, digital humans, and creative production.