About

Alstroemeria lets you create and translate subtitles for any video, complete with voiceover generation.
Powered by Faster-Whisper, Argos Translate, Coqui TTS, and QFluentWidgets.

This project was originally developed for a family member and is provided as is.
It may not receive regular updates, new features, or bug fixes.

---

License

This project is licensed under the GNU General Public License v3.0 (GPLv3).
See the LICENSE file for details.

---

Features

• Subtitle creation – Generate subtitles for any video using Faster-Whisper, with multiple model choices.
• Subtitle translation – Translate subtitles into any language supported by Argos Translate.
• Voiceover generation – Turn subtitles into voiceovers with Coqui TTS.
• GPU acceleration – Optimized for NVIDIA GPUs, with CPU fallback for smaller models.
• Offline – Works fully locally once models are downloaded.

---

Screenshots

---

Download compiled release

Get the latest Alstroemeria release on the GitHub Releases page.

⚠️ The archive is large and split into three parts (.7z.001, .7z.002, .7z.003). Download all parts and extract only the first part with 7-Zip — the rest will combine automatically.

Getting Started

Prerequisites

• Python 3.12
• Git
• Windows

Installation

1. Clone the repository:

   git clone https://github.com/icosane/alstroemeria.git

   Or download the latest .zip release and extract it.

2. Create a virtual environment:

   python -m venv .venv

3. Activate it:

   .\Scripts\activate

4. Install dependencies:

   pip install -r requirements.txt

Alternatively, open the folder in Visual Studio Code or VSCodium, install the Python extension, then press Ctrl+Shift+P → Python: Create Environment → .venv → select requirements.txt.

---

Optional: Build Executable (.exe)

1. Install PyInstaller:

   pip install pyinstaller

2. Build:

   pyinstaller build.spec

   (The build.spec file is included in the repository.)

---

Usage

• The first launch may take longer while directories and environment variables are created. Later launches will be faster.
• Drag & drop any video or .srt file into the window.
• You can then:
  • Create subtitles
  • Translate them
  • Generate a voiceover (video file required, since it uses the original audio)

⚙️ Before starting, configure your preferred Whisper model and translation languages in Settings.

---

Acknowledgments

• Faster-Whisper

• QFluentWidgets

• Argos Translate

• Coqui TTS

• FFmpeg

• PyQt6

• nvidia-cublas

• nvidia-cuda-runtime

• nvidia-cudnn

• pywinrt

• psutil

• onnxruntime

• PyTorch

• pydub

• langdetect

• PyInstaller

• Manuka icons – created by Paul J. (Flaticon)

  This software contains source code provided by NVIDIA Corporation.