Cette page est affichée en anglais. Une traduction française est en cours.
SkillsMar 29, 2026·2 min de lecture

VideoCaptioner — AI Subtitle Pipeline

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

Script Depot
Script Depot · Community
Prêt pour agents

Installation agent prête

Cet actif peut être installé après choix du runtime, vérification du plan et exécution de la commande adaptée.

Native · 98/100Policy : autoriser
Surface agent
Tout agent MCP/CLI
Type
Skill
Installation
Single
Confiance
Confiance : Established
Point d'entrée
VideoCaptioner — AI Subtitle Pipeline
Commande d'installation directe
npx -y tokrepo@latest install d12d8441-f0da-4d3d-a0c2-0f258b27336f --target codex

À exécuter après confirmation du plan en dry-run.

TL;DR
VideoCaptioner combines Whisper transcription, LLM-based correction, 99-language translation, and styled subtitle export in a single desktop application.
§01

What it is

VideoCaptioner is an open-source desktop application that automates the video subtitle workflow. It chains Whisper-based speech recognition, LLM-powered text correction, translation into 99 languages, and styled subtitle export (SRT, ASS, VTT) into a single pipeline. The tool provides a GUI for configuring each stage.

VideoCaptioner targets content creators, video editors, and localization teams who need accurate subtitles across languages. It handles the full lifecycle from raw audio to production-ready subtitle files without manual transcription or separate translation tools.

§02

How it saves time or tokens

Manual subtitle creation involves transcribing audio, correcting recognition errors, translating to target languages, and formatting subtitle files. VideoCaptioner automates all four stages. The LLM correction step catches Whisper's common errors (proper nouns, technical terms, homophones) without human review. Batch processing handles multiple videos sequentially.

§03

How to use

  1. Download the latest release from GitHub or clone the repo and install dependencies with pip install -r requirements.txt.
  2. Run python main.py to open the GUI. Configure your Whisper model and LLM API settings.
  3. Load a video file, select source and target languages, and start the pipeline.
§04

Example

# Clone and set up
git clone https://github.com/WEIFENG2333/VideoCaptioner.git
cd VideoCaptioner
pip install -r requirements.txt
python main.py

# Pipeline stages:
# 1. Whisper transcribes audio to text
# 2. LLM corrects transcription errors
# 3. Translation to selected languages
# 4. Export as SRT, ASS, or VTT with styling
StageInputOutput
TranscriptionVideo/audio fileRaw text with timestamps
CorrectionRaw transcriptCleaned transcript
TranslationCleaned textMulti-language text
ExportTranslated textSRT/ASS/VTT files
§05

Related on TokRepo

§06

Common pitfalls

  • Whisper accuracy depends heavily on audio quality. Background music, overlapping speakers, and low-quality microphones reduce transcription accuracy.
  • LLM correction requires API access (OpenAI or compatible). Without it, you get raw Whisper output which may contain errors for domain-specific vocabulary.
  • Translation quality varies by language pair. Common pairs (English-Spanish, English-Chinese) produce better results than less common language combinations.

Questions fréquentes

Which Whisper model should I use?+

The large-v3 model provides the best accuracy but requires more GPU memory and processing time. The medium model offers a good balance for most content. For fast processing with acceptable quality, use the small model.

What LLM providers does VideoCaptioner support?+

VideoCaptioner supports OpenAI API and compatible endpoints. You can configure any OpenAI-compatible API (including local models via Ollama or LM Studio) for the correction and translation stages.

Can VideoCaptioner process audio-only files?+

Yes. VideoCaptioner accepts both video and audio files. For audio-only inputs, it skips the video processing and goes directly to transcription.

What subtitle formats does it export?+

VideoCaptioner exports SRT (SubRip), ASS (Advanced SubStation Alpha with styling), and VTT (WebVTT for web video). ASS format supports custom fonts, colors, and positioning.

Does VideoCaptioner run on GPU?+

Yes, when a CUDA-compatible GPU is available. Whisper uses GPU acceleration for faster transcription. The tool falls back to CPU processing if no GPU is detected, but processing time increases significantly.

Sources citées (3)
En lien sur TokRepo
Video AI toolsContent toolsFeatured workflows
🙏

Source et remerciements

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

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires

Data Juicer — Data Processing Pipeline for Foundation Models

Data Juicer is a data processing toolkit designed for building and curating training datasets for large language models and multimodal models. It provides over 100 composable operators for filtering, deduplication, and quality analysis of text, image, audio, and video data.

Skills
Script Depot

Remotion Captions & Subtitles — AI-Powered Video Subtitles

AI skill for generating and rendering captions in Remotion videos. Supports transcription, word-level timing, and styled subtitle export.

Skills
Skill Factory

Luigi — Python Pipeline Orchestration by Spotify

Luigi is a Python framework for building complex data pipelines with dependency resolution, scheduling, and failure handling built in.

Skills
Script Depot

Pachyderm — Data Versioning and Pipeline Orchestration

Version your data like Git, build reproducible data pipelines triggered by commits, and track lineage from raw input to model output on Kubernetes.

Skills
Script Depot
◈Accueil🔍Rechercher👤Moi