The best gradient web-ui for asr, translation and tts. Easy one click installation. Fully portable.
- Voice Gulliver is an integrated solution for subtitles, translation, and dubbing.
- Add multilingual subtitles to your video with Voice Gulliver. Expansion into the global market is possible!
- You watch world news every morning? Then, try using the live translation function. It supports real-time translation, just like what you see on YouTube.
- Voice Gulliver is equipped with Vocal Remover provided by UVR5 and Meta's Demucs engine.
- Voice Gulliver uses OpenAI Whisper and Microsoft Azure AI.
- Voice Gulliver can be easily installed with one click and provides Gradio Web-UI.
- Experience the highest level of On-Device AI Voice technology.
VOD
tab- Provides integrated environment for YouTube downloader, noise removal, subtitles, translation, and dubbing
- All video/audio formats supported by ffmpeg can be used
- Selectable output audio format (wav, flac, mp3)
- Speech recognition and subtitle creation for 100 languages
- Select subtitle creation options suitable for PC performance (Whisper Model & Compute Type)
- The BGM and sound effects from the original video remain the same in the dubbed video.
- Supports speed, volume, and pitch adjustment of dubbing voice
-
Live
tab- Real-time voice recognition & translation support
- Select audio input source such as Mic, Speaker, etc.
- Provides the ability to save captured audio, recognized subtitles, and translated subtitles
-
Batch
tab- Batch process large amounts of files
-
Garage
tab- You can upload subtitle file, translate and dub.
- This is useful when you need to proofread subtitles automatically generated by AI.
- Supported subtitle formats: '.ass', '.ssa', '.srt', '.mpl2', '.tmp', '.vtt', '.microdvd', '.json'
- You can download YouTube videos (mp4, webm) and save them as audio files (mp3, wav, flac).
- You can increase the accuracy of voice recognition by removing noise and separating vocals. MDX-Net and Meta's Demucs are used.
- One-click installation. Once installed, you can use it permanently at no additional cost. (※ Free version has 30 minute limit on usage time)
- Provides Web-UI. Google Chrome browser is recommended.
- OS: Windows 10/11 (64bits) ※ Linux and Mac OS are not supported.
- CPU: Intel processor 2GHz or higher (or equivalent compatible)
- RAM: 4GB or more
- HDD: At least 20GB of free space during installation
- GPU: NVIDIA graphics card supporting CUDA 12.1 recommended. VRAM 4GB or more. 8GB or more recommended.
- Internet connection required (installation and translation work)
-
A. Paid version
- Unzip the compressed file (voice-gulliver-x.zip) included in the USB to an appropriate location on your computer.
- Or, copy the already unzipped folder (voice-gulliver-x) to an appropriate location on your computer.
-
B. Free version
- [
](https://github.com/abus-aikorea/voice-gulliver/ Download and unzip the latest release (Source code (zip)) from
- Or, download source code with git clone
- [
git clone https://github.com/abus-aikorea/voice-gulliver.git
- Run
configure.bat
- Install ffmpeg and CUDA (if using NVIDIA GPU) on Windows.
- You only need to run it the first time.
- Run
start.bat
- Start Voice-Gulliver. Web-UI will run automatically.
- When running for the first time, Voice-Gulliver is installed first.
- Voice-Gulliver installation requires an Internet connection, and depending on the system, installation may take more than an hour.
- Never close the Windows-Command window during installation.
- If a problem occurs during installation, delete the installer_files folder and run start.bat again.
ABUS-voice-gulliver-live-jp-ko-subtitle.mp4
-
Run
uninstall.bat
:- Remove the installer_files folder.
- Remove ffmepg and CUDA packages installed on Windows (if selected)
-
Voice-Gulliver has portable installation as standard. To uninstall the program, deleting the installation folder is sufficient.
- Close the Windows-Commnad window and run start.bat again.
- Run the browser directly and enter the address displayed in the Windows-Command window (e.g. http://127.0.0.1:7892) in the address bar.
- Check the GPU memory status in Windows Task Manager - Performance tab.
- Set the Denoise level to 0 or 1. Denoise level 2 requires at least 8GB of GPU memory.
- Set Compute Type to int type. The float type has better quality, but requires more GPU memory.
- The quality of subtitles tends to improve with larger Whisper models, but this is not necessarily the case. large > medium > small > base > tiny
- Among compute types, float type has good performance. The int type is a model that reduces GPU usage and increases speed through model quantization. On the other hand, performance decreases.
- If you increase the denoise level, more background sounds will be removed, and only the remaining voice will be used for voice recognition. It does not always guarantee good results.
When Windows Defender mistakenly recognizes a batch file as a Trojan, this is often called a 'False Positive'. To solve this problem, you can go through the following steps:
- File exception handling: In Windows Defender, you can set certain files or processes to skip security scanning. To do this, follow the steps below:
- Click the ‘Start’ button and go to ‘Settings’.
- Click ‘Update & Security’.
- Select ‘Windows Security’ and go to ‘Virus & threat protection’.
- Click ‘Manage Virus & Threat Protection Settings’.
- Select 'Add exception' in 'Virus & threat protection settings'.
- Select 'File or Folder', find the batch file in question and add it as an exception.
- Temporarily disable Windows Defender: This may be a temporary solution. However, you must be careful when using this method as it may expose your computer to other threats.
- Report the problem to anti-virus software: If you are sure that the file is not a Trojan horse, you can report it to Microsoft as a False Positive. Microsoft will review this and take any necessary action.
- e-mail: [email protected]
- homepage(Korean): https://abuskorea.imweb.me
- 네이버 스마트스토어 (S/W): https://smartstore.naver.com/abus/products/10385660040
- 네이버 스마트스토어 (Solution): https://smartstore.naver.com/abus/products/10298346364
- Coupang(Korean): https://www.coupang.com/vp/products/7875503674
- Amazon(US): https://www.amazon.com/dp/B0D5H8Z4FL
- Amazon(Japan): https://www.amazon.co.jp/dp/B0CTHT2JH3
- Product Information: https://youtu.be/heEN4UIQLjc
- Automatic Subtitle∙Translation: https://youtu.be/uQ14hoEiI4c?si=Io9K_vIDYyeu9Z8_
- Home Karaoke: https://youtube.com/playlist?list=PLwx5dnMDVC9bVxfGo58U-R-w3fUHqwiD6&si=TZBh5AFjcr7_dyiI
- FacebookResearch Demucs: https://github.com/facebookresearch/demucs
- yt-dlp: https://github.com/yt-dlp/yt-dlp
- gradio: https://github.com/gradio-app/gradio
by ABUS