Project Introduction (Try the online version now!)
Klic Studio is a versatile audio and video localization and enhancement solution developed by Krillin AI. This minimalist yet powerful tool integrates video translation, dubbing, and voice cloning, supporting both landscape and portrait formats to ensure perfect presentation on all major platforms (Bilibili, Xiaohongshu, Douyin, WeChat Video, Kuaishou, YouTube, TikTok, etc.). With an end-to-end workflow, you can transform raw materials into beautifully ready-to-use cross-platform content with just a few clicks.
🎯 One-click Start: No complex environment configuration required, automatic dependency installation, ready to use immediately, with a new desktop version for easier access!
📥 Video Acquisition: Supports yt-dlp downloads or local file uploads
📜 Accurate Recognition: High-accuracy speech recognition based on Whisper
🧠 Intelligent Segmentation: Subtitle segmentation and alignment using LLM
🔄 Terminology Replacement: One-click replacement of professional vocabulary
🌍 Professional Translation: LLM translation with context to maintain natural semantics
🎙️ Voice Cloning: Offers selected voice tones from CosyVoice or custom voice cloning
🎬 Video Composition: Automatically processes landscape and portrait videos and subtitle layout
💻 Cross-Platform: Supports Windows, Linux, macOS, providing both desktop and server versions
The image below shows the effect of the subtitle file generated after importing a 46-minute local video and executing it with one click, without any manual adjustments. There are no omissions or overlaps, the segmentation is natural, and the translation quality is very high.
subtitle_translation.mp4 |
tts.mp4 |
agi.mp4 |
All local models in the table below support automatic installation of executable files + model files; you just need to choose, and Klic will prepare everything for you.
| Service Source | Supported Platforms | Model Options | Local/Cloud | Remarks |
|---|---|---|---|---|
| OpenAI Whisper | All Platforms | - | Cloud | Fast speed and good effect |
| FasterWhisper | Windows/Linux | tiny/medium/large-v2 (recommended medium+) |
Local | Faster speed, no cloud service cost |
| WhisperKit | macOS (M-series only) | large-v2 |
Local | Native optimization for Apple chips |
| WhisperCpp | All Platforms | large-v2 |
Local | Supports all platforms |
| Alibaba Cloud ASR | All Platforms | - | Cloud | Avoids network issues in mainland China |
✅ Compatible with all cloud/local large language model services that comply with OpenAI API specifications, including but not limited to:
- OpenAI
- Gemini
- DeepSeek
- Tongyi Qianwen
- Locally deployed open-source models
- Other API services compatible with OpenAI format
- Alibaba Cloud Voice Service
- OpenAI TTS
Input languages supported: Chinese, English, Japanese, German, Turkish, Korean, Russian, Malay (continuously increasing)
Translation languages supported: English, Chinese, Russian, Spanish, French, and 101 other languages
First, download the executable file that matches your device system from the Release, then follow the tutorial below to choose between the desktop version or non-desktop version. Place the software download in an empty folder, as running it will generate some directories, and keeping it in an empty folder will make management easier.
【If it is the desktop version, i.e., the release file with "desktop," see here】
The desktop version is newly released to address the issues of new users struggling to edit configuration files correctly, and there are some bugs that are continuously being updated.
- Double-click the file to start using it (the desktop version also requires configuration within the software)
【If it is the non-desktop version, i.e., the release file without "desktop," see here】
The non-desktop version is the initial version, which has a more complex configuration but is stable in functionality and suitable for server deployment, as it provides a UI in a web format.
- Create a
configfolder within the folder, then create aconfig.tomlfile in theconfigfolder. Copy the contents of theconfig-example.tomlfile from the source code'sconfigdirectory intoconfig.toml, and fill in your configuration information according to the comments. - Double-click or execute the executable file in the terminal to start the service
- Open your browser and enter
http://127.0.0.1:8888to start using it (replace 8888 with the port you specified in the configuration file)
【If it is the desktop version, i.e., the release file with "desktop," see here】
Due to signing issues, the desktop version currently cannot be double-clicked to run or installed via dmg; you need to manually trust the application. The method is as follows:
- Open the terminal in the directory where the executable file (assuming the file name is KlicStudio_1.0.0_desktop_macOS_arm64) is located
- Execute the following commands in order:
sudo xattr -cr ./KlicStudio_1.0.0_desktop_macOS_arm64
sudo chmod +x ./KlicStudio_1.0.0_desktop_macOS_arm64
./KlicStudio_1.0.0_desktop_macOS_arm64
【If it is the non-desktop version, i.e., the release file without "desktop," see here】
This software is not signed, so when running on macOS, after completing the file configuration in the "Basic Steps," you also need to manually trust the application. The method is as follows:
- Open the terminal in the directory where the executable file (assuming the file name is KlicStudio_1.0.0_macOS_arm64) is located
- Execute the following commands in order:
This will start the service
sudo xattr -rd com.apple.quarantine ./KlicStudio_1.0.0_macOS_arm64 sudo chmod +x ./KlicStudio_1.0.0_macOS_arm64 ./KlicStudio_1.0.0_macOS_arm64
This project supports Docker deployment; please refer to the Docker Deployment Instructions
If you encounter issues with video downloads
Please refer to the Cookie Configuration Instructions to configure your Cookie information.
The quickest and easiest configuration method:
- Fill in
transcribe.provider.namewithopenai, so you only need to fill in thetranscribe.openaiblock and the large model configuration in thellmblock to perform subtitle translation. (app.proxy,model, andopenai.base_urlcan be filled in as needed)
Using a local speech recognition model configuration method (balancing cost, speed, and quality):
- Fill in
transcribe.provider.namewithfasterwhisper,transcribe.fasterwhisper.modelwithlarge-v2, and then fill in thellmblock with the large model configuration to perform subtitle translation. The local model will be automatically downloaded and installed. (app.proxyandopenai.base_urlare the same as above)
Text-to-speech (TTS) is optional; the configuration logic is the same as above. Fill in tts.provider.name, and then fill in the corresponding configuration block under tts. The voice codes in the UI should be filled in according to the documentation of the selected provider (the documentation address is in the common questions section below). Filling in Alibaba Cloud's AccessKey, Bucket, AppKey, etc., may be repetitive to ensure a clear configuration structure.
Note: If using voice cloning, tts only supports selecting aliyun.
For obtaining Alibaba Cloud AccessKey, Bucket, and AppKey, please read: Alibaba Cloud Configuration Instructions
Please understand that the task = speech recognition + large model translation + voice service (TTS, etc., optional), which will help you understand the configuration file better.
Please visit Frequently Asked Questions
- Do not submit useless files, such as .vscode, .idea, etc.; please use .gitignore to filter them out.
- Do not submit config.toml; instead, submit config-example.toml.
- Join our QQ group for questions: 754069680
- Follow our social media accounts, Bilibili, where we share quality content in the AI technology field every day.