Source: https://seerepo.com/compare/abus-aikorea/voice-pro/vs/jianchang512/pyvideotrans
Markdown source: https://seerepo.com/compare/abus-aikorea/voice-pro/vs/jianchang512/pyvideotrans.md
Description: voice-pro and pyvideotrans share 14 technologies: Hugging Face, Rich, Gradio, diffusers, openai-whisper, librosa, onnxruntime, transformers, azure-cognitiveservices-speech, edge-tts, faster-whisper, ModelScope, ffmpeg-python, and markdown. Both are written in Python.

# voice-pro vs pyvideotrans

voice-pro and pyvideotrans share 14 technologies: Hugging Face, Rich, Gradio, diffusers, openai-whisper, librosa, onnxruntime, transformers, azure-cognitiveservices-speech, edge-tts, faster-whisper, ModelScope, ffmpeg-python, and markdown. Both are written in Python.

- [abus-aikorea/voice-pro](https://seerepo.com/r/abus-aikorea/voice-pro): Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
- [jianchang512/pyvideotrans](https://seerepo.com/r/jianchang512/pyvideotrans): Translate the video from one language to another and embed dubbing & subtitles.

## What they share and what sets them apart

- In common: Hugging Face, Rich, Gradio, diffusers, openai-whisper, librosa, onnxruntime, transformers, azure-cognitiveservices-speech, edge-tts, faster-whisper, ModelScope, ffmpeg-python, markdown
- Only in voice-pro: Lightning, matplotlib, browser-cookie3, conformer, evaluate, jiwer, misaki, pyworld, f5-tts, x-transformers, azure-ai-translation-text, demucs, kokoro, wetext, torchcodec, yt-dlp, structlog
- Only in pyvideotrans: h5py, oss2, pyarrow, OpenAI, ElevenLabs, Google, anyio, pyside6, AIOHTTP, cycler, fonttools, contourpy, matplotlib-inline, prompt-toolkit, cryptography, itsdangerous, oauthlib, requests-oauthlib, accelerate, bitsandbytes, datasets, Keras, llvmlite, nagisa, peft, piper-tts, scikit-learn, soynlp, speechrecognition, tiktoken, torch, gradio-client, torchaudio, safetensors, dashscope, funasr, sentencepiece, ctranslate2, gtts, litellm, pyannote-audio, imageio, imageio-ffmpeg, jinja2, markdown-it-py, markupsafe, mdurl, pillow, av, annotated-types, marshmallow, Pydantic, coloredlogs, tencentcloud-sdk-python, Alibaba Cloud, psutil

## Side by side

| | voice-pro | pyvideotrans |
|---|---|---|
| Size | 40,077 lines written, 186 code files | 73,829 lines written, 447 code files |
| Who writes it | 5.1% of its commits signed by AI. With Claude Code | 0.8% of its commits signed by AI. With Claude Code and Cursor |
| Activity | Last push July 13, 2026, 118 commits, 13,419 stars | Last push November 5, 2026, 1,526 commits, 19,644 stars |
| Tests | 0 test files | 57 test files. 17% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, voice-pro or pyvideotrans?

pyvideotrans, with 73,829 lines written; voice-pro has 40,077.

The proof: [jianchang512/pyvideotrans's code at commit 7921c81](https://github.com/jianchang512/pyvideotrans/tree/7921c819f9f09ac64a611d57cd676df28fd0b56a)

### Which has more GitHub stars, voice-pro or pyvideotrans?

pyvideotrans, with 19,644 stars; voice-pro has 13,419.

The proof: [jianchang512/pyvideotrans on GitHub](https://github.com/jianchang512/pyvideotrans)

### Which has more tests, voice-pro or pyvideotrans?

pyvideotrans, with 57 test files.

The proof: [jianchang512/pyvideotrans's code at commit 7921c81](https://github.com/jianchang512/pyvideotrans/tree/7921c819f9f09ac64a611d57cd676df28fd0b56a)

### Which was updated more recently, voice-pro or pyvideotrans?

pyvideotrans: its last push was on November 5, 2026, and voice-pro's on July 13, 2026.

The proof: [jianchang512/pyvideotrans's commits on GitHub](https://github.com/jianchang512/pyvideotrans/commits)

### Which has more commits signed by AI, voice-pro or pyvideotrans?

voice-pro: an AI signed 5.1% of its commits, with Claude Code; in pyvideotrans, 0.8%.

## Sources

- abus-aikorea/voice-pro: Read on November 10, 2026, at commit 7231384 (https://github.com/abus-aikorea/voice-pro/tree/7231384f797091dc0d6d0470360fc6fcc2095d0c)
- jianchang512/pyvideotrans: Read on November 5, 2026, at commit 7921c81 (https://github.com/jianchang512/pyvideotrans/tree/7921c819f9f09ac64a611d57cd676df28fd0b56a)

## 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.