subtitles

harry0703/MoneyPrinterTurbo

One-click AI pipeline turns a topic into a finished short video — MoneyPrinterTurbo automates script writing, footage matching, subtitles, and background music to produce HD short videos from just a topic or keyword. It now integrates Kimi K3, a large open multimodal model, to drive script writing and footage keyword selection for better-matched clips. Useful for creators automating TikTok, Reels, or YouTube Shorts production.

laoma528/awesome-zhuiju-free

A curated, daily-checked list of free, ad-free streaming resources — This Chinese-language awesome-list curates 124+ free, ad-free streaming resources: online video sites, apps, cloud-drive search, magnet/BT links, subtitles, TVBox/影视仓 configs, and IPTV sources. A daily automated check verifies link availability, and the community maintains entries openly, making it useful for anyone tired of broken or ad-heavy streaming guides.

abus-aikorea/voice-pro

One Gradio UI for TTS, Voice Cloning, Whisper, and Dubbing — Voice-Pro bundles Edge-TTS/Kokoro TTS, zero-shot voice cloning (E2/F5-TTS, CosyVoice), Whisper-based transcription, YouTube download, Demucs vocal isolation, and multilingual translation into one Gradio web app. It targets creators and developers who want an end-to-end pipeline for subtitling, dubbing, and podcast/audiobook production without stitching separate tools together.

nexmoe/VidBee

Download video and audio from 1000+ sites, transcribe locally with speaker labels, and summarize, translate, or chat with your media using your preferred AI provider.

zhouxiaoka/autoclip

Turn one link into ready-to-post short videos — AutoClip is an open-source desktop app that converts long podcasts, interviews or lectures into platform-ready short clips with subtitles, covers and captions for Douyin, Xiaohongshu, TikTok, Reels and YouTube Shorts. Rendering runs locally; only cloud AI models are pay-per-use, and an editor is available for fine-tuning.

JuneYaooo/rea-video

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. 逆向一切视频，逐个镜头看是拍的、AI 生成的还是代码做的，再告诉你怎么复刻。

denizsafak/abogen

Generate audiobooks from EPUBs, PDFs and text with synchronized captions.

kajisho5/ffmpeg-skill

42 local FFmpeg tools that let coding agents edit and verify video — This gives Claude Code, Cursor, Codex or any MCP client a local video editor: 42 FFmpeg tools with a machine-readable contract, exposed via an MCP server or npx install. It covers cutting, captions, reframing, loudness normalization and platform exports, with no cloud dependency or API keys, so agents can edit footage and check their own output.

tmoroney/auto-subs

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

pluja/whishper

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

wquguru/cicada

知了 Cicada · 任何会议和直播的实时字幕、同声传译、AI 会议纪要，Mac、Windows、Linux、Android 免费开源。Live subtitles, interpreting and meeting notes for any call or stream, on Mac, Windows, Linux and Android.

yuxino/Mimi

Cross-platform live subtitles that translate system or mic audio in real time — Mimi is a Tauri/Rust desktop and Android app that captures computer or microphone audio and overlays real-time translated subtitles. It supports macOS, Windows, Linux (PipeWire/PulseAudio) and Android, making it useful for watching foreign-language videos, calls or streams without separate subtitle files.

oboroge0/hayamimi

CPU-only multilingual live transcription that beats Whisper on Japanese CER — hayamimi routes each utterance to a specialist quantized ONNX model per language via sherpa-onnx instead of one general Whisper model, hitting 3.8% CER on Japanese broadcast audio vs Whisper-large-v3-turbo's 13.8%, at 10-50x realtime on a 6-core CPU, under 2GB RAM, with no GPU or cloud API.

lonthq/overtone-captions

One caption file, automatically re-cut for every aspect ratio — Overtone stores word-level timing once and generates separate caption line breaks per screen shape (16:9, 9:16, or custom), instead of forcing one subtitle layout onto every player. It ships as a CLI that builds the format from audio, video or subtitles, plus a video.js plugin that renders the right cut automatically. Useful for teams repurposing video across landscape and vertical/social formats.