pyVideoTrans

jianchang512/pyvideotrans

Translates videos from one language to another: speech recognition, subtitle translation and dubbing, merged back into the video. Can also do transcription or TTS alone.

Why pick itOffers a no-install packaged build for Windows, works with local Whisper and many translation/TTS services, and is very actively maintained.

Install

InstallWindows: download the prebuilt package; macOS/Linux: git clone, then run uv run sp.py

GitHub: jianchang512/pyvideotrans
Website: pyvideotrans.com
Stars: ★ 19.5k
License: GPL-3.0
Language: Python
Last push: Oct 23, 2026
Category: Creative

Good for

Translate a video into another language in one pass: recognition, subtitle translation, dubbing and merge
Batch-convert audio or video into SRT subtitles with speaker diarization
Give each speaker a different AI voice, or clone voices with F5-TTS or CosyVoice
Pause at each stage to proofread recognition and translation by hand

Getting started

On Windows, download the pre-packaged build, unzip it to a path without Chinese characters or spaces, and run sp.exe
On macOS/Linux, install Python 3.10 and FFmpeg, git clone the repo and run uv run sp.py
Pick recognition, translation and TTS services in the UI, then load a video

Before you install

Don't run it from inside the archive; NVIDIA GPU acceleration needs CUDA 12.8 and cuDNN 9.11. Local Faster-Whisper, Ollama and free Edge-TTS work alongside many online APIs.

Summarized by AI from the project docs; check the official docs before relying on it.

Similar tools

MoneyPrinterTurboCreative · ★ 135k
Automatically generate HD short videos from topics or keywords, including scripts, subtitles, background music, and editing.
ComfyUICreative · ★ 143k
A local GUI and backend for combining image, video and audio generation models as node graphs, supporting the latest models like Flux, Wan and Qwen-Image.
UpscaylCreative · ★ 50.9k
A desktop AI image upscaler that enlarges low-res photos or illustrations 2–16× and restores detail, with batch processing.
IndexTTSCreative · ★ 24.7k
Zero-shot speech synthesis open-sourced by bilibili: clone a voice from a few seconds of reference audio, with control over emotion and exact duration. Strong in Chinese and English.
VideoLingoCreative · ★ 18.9k
One click for speech recognition, sentence segmentation, translation, subtitle alignment and AI dubbing, outputting Netflix-standard single-line subtitles.