Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Image & videoPythonApache-2.0

Huanshere/VideoLingo

VideoLingo is a state-of-the-art automated video localization and generation platform. Leveraging Claude 3.5 Sonnet for deep contextual understanding, it takes any YouTube video or raw footage, transcribes it with WhisperX, segments sentences naturally rather than by rigid word limits, translates into 50+ languages with cultural nuance, generates AI voice dubbing, and clips engaging YouTube Shorts.

13.2k stars1.8k forks35 contributors42 open issuesUpdated

What it does

  • Converts YouTube videos and podcasts into multi-lingual dubbed versions with native fluency.
  • Uses Claude 3.5 Sonnet to achieve human-level subtitle line-breaking and idiom translation.
  • Clips key moments from long YouTube videos into standalone vertical Shorts.
  • Provides one-click Streamlit UI with live preview and custom subtitle typography.

Key features

  • Claude-powered NLP engine for context-aware translation and terminology consistency.
  • WhisperX word-level timestamp alignment with sub-millisecond precision.
  • Voice cloning and TTS dubbing with emotion matching.
  • Direct YouTube link input with automatic stream downloading and processing.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Clone repository
git clone https://github.com/Huanshere/VideoLingo.git
cd VideoLingo
Install dependencies
pip install -r requirements.txt

Supports NVIDIA GPU acceleration via CUDA; CPU mode also available.

Configure Claude API
cp config.example.yaml config.yaml
# Set llm_type: "claude-3-5-sonnet"
# Set ANTHROPIC_API_KEY: "sk-ant-..."

Add Claude 3.5 Sonnet for context-preserving translations.

Launch Streamlit Dashboard
streamlit run st.py
Claude AI Video Production Guide YouTube & Shorts Workflow

How to generate YouTube videos with Claude AI

How to use Claude 3.5 Sonnet inside VideoLingo to localize, translate, dub, and create viral YouTube Shorts from any video source.

Prerequisites checklist

  • Python 3.10+
  • FFmpeg installed
  • Anthropic API Key (Claude 3.5 Sonnet)
  • NVIDIA GPU (optional for accelerated WhisperX)
1

Install VideoLingo and configure Claude 3.5 Sonnet

Clone the repo and configure config.yaml with your Anthropic API key. Select claude-3-5-sonnet as the translation and segmentation LLM.

Terminal / Command
pip install -r requirements.txt && streamlit run st.py
2

Input YouTube Video URL

Paste the URL of any existing YouTube video or upload an MP4 recording. VideoLingo extracts the audio and runs WhisperX for word-level transcription.

3

Claude AI Semantic Subtitle & Dubbing Scripting

Claude analyzes the full transcript, corrects technical terminology, performs culturally adapted translation, and rewrites the narration to match the exact duration of the original audio.

4

Dubbing & Shorts Clipping

Select target language voice actor, choose 9:16 vertical crop mode for YouTube Shorts, and render the final high-definition dubbed video.

Ready-to-use Claude AI Scripting Prompt

Translate and optimize the following YouTube transcript into natural, idiomatic Hindi/Hinglish. Adjust phrasing so sentence lengths match spoken syllable counts for audio dubbing, and format as timed subtitle blocks with bold keywords highlighted.

Alternatives to consider

VideoLingo is a strong default for image & video, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

MoneyPrinterTurboWhisperXPyAnnote

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

VideoLingo FAQ

Adoption questions we hear most often about this project.

Related repositories

Image & video · Python

A node-based interface for diffusion models with fine-grained control over image and video pipelines.

88.0k9.8kGPL-3.0

Image & video · Python

An open-source effort to reproduce efficient video generation models.

29.0k2.9kApache-2.0