Live Instant Subtitles & Real-time Multi-language Translation
DilMesh is a powerful desktop application that provides real-time speech-to-text and instant translation, capable of broadcasting subtitles to multiple windows simultaneously. It's designed for streamers, presenters, and anyone needing accessible, multilingual communication on the fly.
- 🎙️ Real-time Speech-to-Text: High-accuracy transcription using Google Cloud Speech-to-Text or OpenAI Whisper (Local).
- 🌐 Instant Multi-language Translation: Translate spoken audio into multiple languages simultaneously (e.g., English -> Turkish, Spanish, French) in real-time.
- 🖥️ Multi-Window Broadcasting: Create separate, customizable subtitle windows for different displays or OBS scenes. Each window can display a different language!
- 🎨 Highly Customizable:
- Adjust font size, color, background (chroma key), and positioning.
- Analog VU Meter: Visual audio feedback with peak indicators.
- 🔄 System Tray Integration: Minimized to tray for unobtrusive operation.
- 🚀 Performance Optimized: Built with Electron + Vite + Vue 3 for a snappy experience.
- 🔜 Future API Support: We are actively working on adding more speech-to-text and translation providers (e.g., DeepL, Azure, AWS, and more). Stay tuned!
Control all your settings, transcription status, and active windows from a single place.
Broadcast subtitles to multiple windows or project them fullscreen on specific displays. Each output can have different languages, styles, and positioning.
- Node.js (v18 or higher recommended)
- Node.js (v18 or higher recommended)
- pnpm (This project uses pnpm for package management)
- Google Cloud Platform Account (Optional, for higher accuracy and translation features)
-
Clone the repository:
git clone https://github.com/antlionguard/dilmesh.git cd dilmesh -
Install dependencies:
pnpm install
-
Run in Development Mode:
pnpm dev
To create a distributable application for your OS:
-
macOS (DMG/App):
pnpm build:mac
-
Windows (NSIS/Portable):
pnpm build:win
- Create a project in Google Cloud Console.
- Enable Cloud Speech-to-Text API and Cloud Translation API.
- Create a Service Account and download the JSON Key File.
- In DilMesh, go to Settings -> Transcription Provider -> Google Cloud Platform.
- Paste the contents of your JSON key file.
- Go to Settings.
- Select Local Whisper.
- Choose a model size (
tiny,base,small). Note: Requires downloading the model on first use.
We love contributions! Whether it's fixing bugs, adding new languages, or implementing new features from our roadmap. Please feel free to submit a Pull Request.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
If you find this project useful, you can support its development!
