RepositoryPython
JI

jianchang512/pyvideotrans

Translate the video from one language to another and embed dubbing & subtitles.

19.8kstars
2.5kforks
10issues
12views

Thành tựu nổi bật

Những danh hiệu mới nhất của dự án

1
TINIX TRENDING·Chủ đề: video-transition

#1 Repository Của Tháng

1
TINIX TRENDING·Chủ đề: speech-to-text

#1 Repository Của Tháng

1
TINIX TRENDING·Chủ đề: subtitle-translation

#1 Repository Của Tháng

🌍 AI-Powered Video Translation Made Simple

Translate videos across languages with automatic dubbing, subtitles, and speaker-aware AI voices.

pyVideoTrans is a powerful open-source tool that converts videos from one language to another. It handles the full pipeline: speech recognition, subtitle translation, multi-role AI dubbing, and audio-video sync. Whether you're localizing content or building educational material, it supports both offline models and mainstream online APIs.

✨ Highlights

  • 🎥 One-Click Video Translation: ASR → Subtitle Translation → TTS → Video Synthesis.
  • 🎙️ Audio Transcription: Batch convert audio/video to SRT with speaker diarization.
  • 🗣️ Multi-Role Dubbing: Assign different AI voices to different speakers.
  • 🧬 Voice Cloning: Supports F5-TTS, CosyVoice, GPT-SoVITS for zero-shot cloning.
  • 🧠 Broad Model Support: Includes Faster-Whisper, DeepSeek, ChatGPT, Claude, Gemini, Edge-TTS, and more.
  • 🛠️ Interactive Editing: Pause and proofread at each stage for accuracy.
  • 💻 CLI & WebUI: Run headless on servers or access via browser.
  • 🖥️ Local & Cloud Options: Works offline or with online APIs.

💡 Why it matters

Unlike manual translation workflows, pyVideoTrans automates the entire process while allowing human review at key steps. Its modular design lets users pick the best ASR, LLM, and TTS engines for their needs.

It's ideal for creators, educators, and developers who need fast, accurate video localization without expensive tools.


#VideoTranslation #AIDubbing #OpenSource #TiniX

Similar Projects

Discover other similar projects and AI models.

Modeltext-to-speech
openbmb/VoxCPM2

VoxCPM2 VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. !GitHub(https://img.shields.io/badge/GitHub-VoxCPM-blu...

♥0
972.0k
Nov 9, 2026
RepositoryPython
harry0703/MoneyPrinterTurbo

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

145.1k
Nov 22, 2026
RepositoryPython
unslothai/unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

80.0k
Nov 22, 2026
RepositoryPython
RVC-Boss/GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

64.2k
Nov 11, 2026
RepositoryPython
coqui-ai/TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

46.2k
Aug 16, 2024
RepositoryPython
OpenBMB/VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

42.7k
Nov 9, 2026
RepositoryPython
myshell-ai/OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

38.3k
Apr 19, 2025
RepositoryPython
babysor/MockingBird

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

36.9k
Mar 3, 2026
Modeltext-to-speech
hexgrad/Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be...

♥0
13.3M
Apr 10, 2025