ScriptsMar 29, 2026·2 min read

VideoCaptioner — AI Subtitle Pipeline

LLM-powered video subtitle tool: Whisper transcription + AI correction + 99-language translation + styled subtitle export. 13,800+ stars.

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

Download the latest release from GitHub Releases, or run from source:

git clone https://github.com/WEIFENG2333/VideoCaptioner.git
cd VideoCaptioner
pip install -r requirements.txt
python main.py
Intro

VideoCaptioner is a full subtitle pipeline — it transcribes video audio using Whisper, corrects errors and improves segmentation with an LLM, translates to 99 languages, and exports styled SRT/ASS subtitles. The GUI makes it accessible to non-technical users. 13,800+ GitHub stars.

Best for: Video creators needing accurate multilingual subtitles, translation agencies, content localization Works with: Windows/Mac/Linux, supports all major video formats

Part of the Video AI Toolkit collection.

Pipeline

Video → Whisper (transcription) → LLM (correction & segmentation)
    → Translation (99 languages) → Styled subtitle export (SRT/ASS)

Features

  • Whisper transcription: Multiple backend options for accuracy
  • LLM correction: Fixes recognition errors, improves sentence segmentation
  • 99 languages: Full multilingual translation support
  • Styled output: SRT and ASS format with customizable fonts, colors, positions
  • Batch processing: Process multiple videos in queue
  • GUI: User-friendly interface, no command-line needed

FAQ

Q: What is VideoCaptioner? A: An AI-powered subtitle generation tool that combines Whisper speech recognition with LLM-based correction and 99-language translation. 13,800+ GitHub stars.

Q: Is VideoCaptioner free? A: Yes, the tool is GPL-3.0 licensed. You need API keys for the LLM correction service.

🙏

Source & Thanks

Created by WEIFENG2333. Licensed under GPL-3.0. VideoCaptioner — ⭐ 13,800+

Related Assets

MoneyPrinterTurbo — One-Click Short Video Generator

AI-powered end-to-end short video pipeline: topic in, finished video out. Auto-generates script, materials, subtitles, and background music. 53,000+ stars.

TokRepo精选

Diffusers — Universal Video & Image Generation Hub

Hugging Face's diffusion model library. Run CogVideoX, AnimateDiff, Stable Video Diffusion, and 50+ video/image models with a unified API. 33,200+ stars.

TokRepo精选

Open-Sora — Open-Source Text-to-Video Generation

Open-source alternative to Sora by HPC-AI Tech. Generate videos from text prompts with an 11B parameter model. Apache 2.0 licensed. 28,800+ stars.

TokRepo精选
◈Home🏆Leaderboard👤Me