Lukasz Liniewicz

Pandrator. Turn PDFs and EPUBs into audiobooks; subtitles or videos into dubbed videos (including translation), and more. For free. Pandrator uses local models, including voice-cloning (instant, RVC-enhanced, XTTS fine-tuning) and LLM processing. It aspires to be a user-friendly app with a GUI, an installer and all-in-one packages.

ChaReCo. A tool for concatenating the content of repositories and local folders as plain text to share with Large Language Models in chat interfaces without direct repo access or API integration.

Subdub. A command line Python app offering a video-to-dubbed-video workflow with transcription, translation and synchronisation. Developed for Pandrator.

VoiceCraft_API. Windows-compatible Fast API implementation of VoiceCraft, the Zero-Shot Speech Editing and Text-to-Speech in the Wild

breath-removal. Detect and remove or lower the volume of breathing in speech recordings.

easy_xtts_trainer. A command line utility to easily finetune XTTS models in a fully automated way. Developed for Pandrator.

PyCropPDF. A small GUI app that overlays all pages of a PDF with transparency and enables batch cropping for all or even and odd pages separately as well as page deletion. Intended to help safely remove headers and footers or margins for reading, OCR or other processing.

notes2llm. A browser-based tool for post-processing HTML, CSS, and JavaScript generated by LLMs. Edit text, change image sources, add comments for LLMs, modify CSS, and prepare code for further refinement or implementation.

voxtral-fastapi. FastAPI server and Tkinter GUI wrapper for the Voxtral TTS CLI. Supports chunked speech synthesis, background jobs, voice presets, GGUF/BF16 models, and an OpenAI-compatible audio API.