MurMur is a lightweight desktop app that routes, transcribes, translates into English, and records system audio in real time — entirely locally, with no cloud dependency.

With a simple two-pane interface, spoken input is automatically recognized and displayed almost live as text. Optionally, an English translation is generated at the same time.

A special strength of MurMur lies in its ability to route desktop audio through virtual devices like BlackHole or Loopback, adjust levels with virtual gain, and export recordings directly as MP3. A creative bonus use case is combining it with Shazam for Mac to reliably identify songs playing on the computer — free from any ambient noise.

All processing runs locally on the machine, ensuring maximum data privacy and low latency.

SRT Translator is a desktop tool with a GUI and CLI for precise translation of .srt subtitle files.

It supports three engines: NLLB (Meta’s “No Language Left Behind”) for low system requirements and solid quality; SeamlessM4T (Meta) for higher quality with moderate resource needs; and an experimental mode via Ollama for locally hosted LLMs (highest potential quality, but also the highest hardware demands).

For the Ollama mode, you need Ollama installed and the service running; power users can tweak the prompt directly in the Python file.

(NLLB: arXiv 2207.04672; SeamlessM4T: arXiv 2308.11596; Ollama: official repo.)

This desktop tool allows you to automatically transcribe, summarize, and translate YouTube videos into different languages with just a few clicks – all locally and in compliance with data privacy. Core features include:

• Quick Overview: Video content is automatically captured, transcribed, and summarized using AI for a concise understanding.
• Flexible Translation: Key information is instantly available in your preferred language.
• Knowledge Archive: All transcribed and translated summaries, along with metadata, audio, and text, are archived and searchable (using SQLite).
• Local Processing: No cloud, no data sharing, no sign-up required – you retain full control over your content.
• Efficient Workflow: Ideal for research, notes, quote collections, or permanently saving valuable information from videos.

The tool combines AI-powered automation with a user-friendly interface, providing real value for anyone who wants to efficiently extract and structure information from YouTube videos.

Infinite Sound is an endless music generation tool that creates any sounds based on text inputs using Stable Audio Open. The application offers a minimalist user interface for entering keywords, controlling volume, and managing recordings. Audio snippets are constantly generated and crossfaded, and can be locally saved by activating the “Record” mode.

Technically, the program is based on PyTorch, Stable Audio Tools, and PyWebView, and supports both CPU and GPU acceleration (CUDA/MPS). The AI models necessary for generation are downloaded from Hugging Face on the first launch, for which a free account and an API token are required.

The SD 3D Model Generator is an innovative creative tool that bridges the gap between simple text inputs and fully developed 3D assets for game development, visualization, and creative prototyping. Unlike traditional Stable Diffusion (SD) frontends, this application accelerates the entire workflow by integrating advanced Large Language Models (LLMs):
Prompts are automatically optimized, seamless (topic-relevant) environment maps are generated, images of objects or characters are created and transformed into high-quality 3D models – all in an intuitive interface where you can view images as well as 3D models with environment maps.

What sets the tool apart?

• Prompt-to-Asset, End-to-End: Simply enter an object name or concept – the system guides you through the process, optimizing your prompt for Stable Diffusion via LLM, ensuring stylistic consistency, creative details, and optimal formatting.
• Simplified 3D Workflow: Generated images can be converted to 3D models (GLB) with one click. Additionally, a custom panorama environment (HDRI) can be created for each asset, ready to use in Blender or game engines.
• No prompt experience needed: The LLMs in the backend automatically transform rough ideas into professional, detailed prompts – saving time and reducing creative effort.
• Integrated Gallery & Batch Generation: Extensive collections of images and models can be efficiently managed through batch control, page navigation, and comparison view.

Features & User Experience

• Easy input, professional result: A simple object title (“low poly farmer”) is sufficient – the system uses LLMs to automatically optimize the Stable Diffusion prompts and always delivers the best possible image quality, composition, and clarity.
• Real-time streaming: LLM and image generation results are streamed live to the interface – for transparency and quick feedback.
• Intuitive galleries: Separate, tab-based galleries for 2D images and 3D models – assets can be compared, managed in batch, or edited directly. Context menus allow instant export, reuse of generation results, or direct model/HDRI creation.
• Automatic 3D model creation: Each generated image can be directly converted into a 3D GLB model via the UI (through external tools/scripts, flexibly configurable).
• Automatic environment map creation: A custom equirectangular HDRI environment can be generated for each model: LLMs first describe a suitable environment, then SD creates a photorealistic panorama for lighting and reflections.
• Batch control & placeholders: Support for batch image creation, placeholder management, and clear regeneration – keeping the current progress always traceable.
• One-click export to Blender: Models and HDRIs can be opened and further edited directly from the application in Blender.

Technical Overview

• Frontend:
  • Pure HTML/CSS/JavaScript, seamlessly integrated via PyWebview for direct access to the Python backend.
  • Dynamic, responsive UI logic for gallery, tabs, and context menus.
  • Live streaming of LLM outputs and image generation status via Python–JS bridge.
• Backend:
  • Python backend based on PyWebview and a FastAPI-like interface.
  • Integration of Ollama or local LLM servers (e.g., Mistral) for automatic prompt optimization and summarization.
  • Image generation via Stable Diffusion (diffusers library), all parameters (model, VAE, sampler, etc.) are user-configurable or set automatically.
  • External tools/scripts for converting images to 3D (GLB) and creating HDRI panoramas are modular and easily interchangeable.
  • Automatic file management, metadata embedding (JSON in PNG and sidecars), and monitoring of asset folders for live updates in the gallery.
• Extensibility:
  • Each backend process is decoupled and scriptable: The 3D conversion or HDRI creation can easily be replaced with custom pipelines.
  • Easily adaptable for different LLMs, SD models, or 3D workflows.

The SD 3D Model Generator radically simplifies the path from idea to finished asset. By combining LLMs, Stable Diffusion, and automated 3D workflows, artists, designers, and developers can generate, manage, and process high-quality visuals faster, more flexibly, and more creatively.

Auto-Git is a cross-platform Electron app that automatically monitors and manages Git repos and writes commit messages and documentation / READMEs using LLMs.

• Monitoring & Automatic Commit
  • – Add any folders as Git repositories: Auto-Git takes care of the initial Git setup if needed.
  • – Real-time file watching (Chokidar): As soon as files change, changes are detected in a debounce interval and automatically committed to Git.
  • – Intelligent commit messages: Once a defined line or time threshold is reached, Auto-Git collects all new commits, creates a prompt-optimized input for an Ollama-LLM (qwen2.5-Coder) from their diffs, and replaces the standard commit messages with semantically concise summaries.
• README Generation & Repository Description
  • – At the push of a button or upon initial addition: Auto-Git extracts relevant code files (by size, relevance score, .gitignore rules) and feeds them into an LLM prompt to automatically create or update a complete, well-structured README.md.
  • – LLM-assisted short description (≤ 255 characters): For each folder, Auto-Git can generate a one-liner project description text in fractions of a second using the same Ollama backend.
• Robust Folder Management
  • – Missing or moved folders are automatically detected (“Needs Relocation”), and by clicking on the sidebar icon, you can assign the new path and restore the original Git state (checked via commit hash).
  • – Simple drag-and-drop support: Drag folders directly into the app, instantly initialize a Git repo, and set it to monitoring.
  • – .gitignore management: Typical temporary/IDE/build files are automatically detected (Micromatch + predefined patterns) and added to .gitignore if needed.
• Gitea Integration & Push Workflow
  • – In the settings, a personal Gitea API token can be stored.
  • – When clicking “Push to Gitea”, Auto-Git checks if the remote repo already exists:
    1. Not available → Create repository (with LLM-generated short description).
    2. Available → Update current description via PATCH.
  • – Afterwards, the local remote origin is reconfigured, and the current branch including tags is automatically pushed.
• Desktop UI & Usability
  • – Electron & TailwindCSS: Responsive interface with sidebar (filtered list of all monitored folders), central content area (displays all commits paginated, including diff view, snapshot export, and “Jump Here” checkout).
  • – Sky Mode: Automatic time-dependent background (soft blue during the day, dark blue at night).
  • – Tray Menu & Tray Icon: App minimized to tray, right-clicking on the tray icon allows quick starting/stopping of monitoring per folder, adding/removing folders, “Quit”.
  • – Settings Dialog:
    • > Sky theme on/off
    • > “Close to Tray”: Hides window when closing, instead of actually quitting the app
    • > Automatic startup behavior
    • > Intelligent commit thresholds (lines and minutes)
    • > Selection of used Ollama models (commit vs. README)
    • > Store Gitea API token
  • – Gamification & Live Statistics: Daily counter for commits, color-increasing visualization (“Commits today”), live countdown until the next automatic LLM commit.
• Technology Stack
  • – Frontend: Electron + HTML/CSS + TailwindCSS + a custom minimal-animated “Anime Cat” (client-side cat streaming for LLM responses).
  • – Backend/Node:
    • > chokidar for file watching
    • > simple-git for all Git operations (Init, Status, Commit, Diff, Rebase, Push, Remote Config)
    • > micromatch & ignore for filtering files/folders
    • > electron-store for persistence of all settings (including Gitea token, sky mode, thresholds, model selection)
    • > Custom LLM integration: Start/Stop Ollama server, parallel stream handling via fetch(…).getReader().
    • > Tray/Menu integration with native Electron menus and context menus in sidebar/treeview.

All features – from continuous, automatic commit creation to fully automated push-and-repo setup on Gitea – are designed to make developers’ everyday lives easier: You can continue to focus on code while Auto-Git ensures that commit history, documentation, and remote repositories are always up to date.

From 2015 to 2019, I engaged intensively with artificial intelligence, virtual humanoids, human-machine interactions, and the resulting philosophical and cultural questions during my studies at the University of Fine Arts Saar in Saarbrücken. I dealt with the limits and misunderstandings in dealing with AI technologies both theoretically and practically as an artist.

In my bachelor’s thesis “Comparison between Artificial and Real Intelligence” (2017, final grade 1.0), I explored how digital avatars simulate learning processes using genetic algorithms and compared these with the real learning and pain experiences of a human performer. The performance “Learning” utilized the optical Pepper’s Ghost effect for the spatial representation of a digital character. The results clearly highlighted the emotional gap between technical simulation and human experience.

In my master’s thesis, I expanded this approach and delved deeper into the perception and staging of virtual characters and their interactions with humans. Among other things, the following projects emerged:

• Gerkzeuk (2016): A computer-controlled object that autonomously downloads, modifies, and sells images from the internet. This object raised fundamental questions about authorship, machine ethics, and the role of the artist. Through a holographic representation (“Iris”), the machine artist was additionally given a human-like persona.
  Link to project page
  
• Pepper’s Ghost Crystals (since 2016): Interactive showcases that holographically depict virtual humanoids and are equipped with facial recognition, emotion analysis, and speech recognition software. This work intensely researched making artificial and human interaction tangible.
  Link to project page
  
• Comparison between Artificial and Real Intelligence (2017): A performance in which a digital character, using genetic algorithms, attempts to learn basic motor skills in parallel with a human performer. The work clearly reveals the differences and emotional dimensions between digital simulation and human experience.
  Link to project page
  
• Anti-Art (2019): A deliberately simple apparatus with a puppet, controlled by unpredictable impulses, humorously and critically reflects the hype around AI technologies and their frequent overestimation.
  Link to project page
  
• Spatial Installation for the Master’s Exhibition (2019): In a scenographic situation, I subjected visitors to a reflective interaction by automatically photographing them and projecting their faces, making themes such as self-perception, data protection, and echo chambers tangible.
  Link to project page

These projects were accompanied by theoretical reflections on transparency in design, black box issues, random and deterministic systems, as well as ethical and philosophical dimensions of AI. Inspired by references such as Frieder Nake, Andrew Glassner, and Richard David Precht, I critically engaged with terms and misunderstandings surrounding artificial intelligence, artificial life, and consciousness.

From my artistic research, the following central insights emerged:

• AI technologies can imitate human behavior, but they do not generate genuine emotional depth or authentic empathy. The illusion of human interaction created by machines always remains on a superficial level.
• The misuse of metaphorical terms from biology and neuroscience in technology (such as “neural network” or “intelligence”) significantly contributes to misunderstandings and a mythical overestimation of technical possibilities.
• The use of transparency design and the disclosure of technical processes are essential to alleviate fears and promote critical thinking towards modern technologies.
• Randomness and unpredictability in technical systems often create a perception of magic or autonomy, which can lead to overinterpretation of technical capabilities.
• The cultural and societal reception of AI technologies and virtual characters is strongly influenced by projections and fantasies that are deeply rooted in our psychological tendency to perceive human-like qualities in technical artifacts.
• Despite the apparent autonomy of software and machines, the responsibility always lies with the human who designs, programs, and operates these systems. Machines and software remain tools and will never become independent subjects.
• The question of the meaning of “life” gains new depth through engagement with autonomous and self-reproducing programs like the “Forkbomb” and challenges classical biological definitions.
• Psychologically, the work of scientists, IT technicians, and artists often reveals an unconscious motivation to create artificial beings, comparable to the “womb envy” discussed in psychology. This reflects the deep need to creatively produce life or living systems.
• Object-oriented programming opens up the possibility of reconstructing virtual worlds and invites reflection on the boundaries between reality and simulation.

My work between 2015 and 2019 thus represents a versatile, critical, and innovative engagement with humanity, technology, and their complex relationships, aiming to contribute to a well-founded and reflective public discourse on these topics.