Source: https://seerepo.com/r/WEIFENG2333/VideoCaptioner/built
Markdown source: https://seerepo.com/r/WEIFENG2333/VideoCaptioner/built.md
Description: VideoCaptioner is a Python repo. It uses AI through edge-tts, langdetect, ModelScope, and OpenAI and makes its content with pillow and yt-dlp.

# What is VideoCaptioner built with?

VideoCaptioner is a Python repo. It uses AI through edge-tts, langdetect, ModelScope, and OpenAI, makes its content with pillow and yt-dlp, deploys with psutil, and uses diskcache. It has 37,988 written lines, with 44 test files.

Read on November 7, 2026, at commit 95842ec.

Repository: https://github.com/WEIFENG2333/VideoCaptioner

## Frontend

### Styles

- **[fonttools](https://seerepo.com/uses/fonttools)**: 2 files

### Interface

- **pyqt5**: 36 files

## Backend

### Data

- **diskcache**: 1 file

### AI

- **edge-tts**: 1 file
- **[langdetect](https://seerepo.com/uses/langdetect)**: 1 file
- **[ModelScope](https://seerepo.com/uses/modelscope)**: 1 file

### Services

- **[OpenAI](https://seerepo.com/uses/openai)**: 6 files · [videocaptioner/core/dubbing/rewriter.py, line 6](https://github.com/WEIFENG2333/VideoCaptioner/blob/95842ecb5618c0b6a548a336bdfb0eb859bdb501/videocaptioner/core/dubbing/rewriter.py#L6)

## Support

### Content

- **[pillow](https://seerepo.com/uses/pillow)**: 4 files
- **[yt-dlp](https://seerepo.com/uses/yt-dlp)**: 3 files

### Deploy

- **[psutil](https://seerepo.com/uses/psutil)**: 1 file

### Other

- **requests**: 11 files
- **pydub**: 3 files
- **json-repair**: 2 files
- **platformdirs**: 2 files
- **tenacity**: 1 file
- **tomli**: 1 file

## Other repos with a similar stack

- [debpalash/VoiceStudio](https://seerepo.com/r/debpalash/VoiceStudio/built): OpenAI, ModelScope, pillow, yt-dlp, psutil · [Compare](https://seerepo.com/compare/debpalash/VoiceStudio/vs/WEIFENG2333/VideoCaptioner)
- [Aider-AI/aider](https://seerepo.com/r/Aider-AI/aider/built): diskcache, OpenAI, fonttools, pillow, psutil · [Compare](https://seerepo.com/compare/Aider-AI/aider/vs/WEIFENG2333/VideoCaptioner)
- [assafelovic/gpt-researcher](https://seerepo.com/r/assafelovic/gpt-researcher/built): OpenAI, fonttools, langdetect, pillow, psutil · [Compare](https://seerepo.com/compare/assafelovic/gpt-researcher/vs/WEIFENG2333/VideoCaptioner)
- [Significant-Gravitas/AutoGPT](https://seerepo.com/r/Significant-Gravitas/AutoGPT/built): OpenAI, pillow, yt-dlp, psutil · [Compare](https://seerepo.com/compare/Significant-Gravitas/AutoGPT/vs/WEIFENG2333/VideoCaptioner)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): OpenAI, pillow, yt-dlp, psutil · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/WEIFENG2333/VideoCaptioner)
- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): OpenAI, ModelScope, pillow, psutil · [Compare](https://seerepo.com/compare/run-llama/llama_index/vs/WEIFENG2333/VideoCaptioner)

## Frequently asked questions

### What language is VideoCaptioner written in?

VideoCaptioner is written in Python, with 37,988 written lines.

### Does VideoCaptioner use AI?

Yes. VideoCaptioner uses AI through edge-tts, langdetect, ModelScope, and OpenAI.

### What services does VideoCaptioner use?

VideoCaptioner uses diskcache.

### Does VideoCaptioner have tests?

Yes. VideoCaptioner has 44 test files.

### Which repos have a stack like VideoCaptioner's?

The ones that share most of its stack: debpalash/VoiceStudio, Aider-AI/aider, and assafelovic/gpt-researcher.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.