LoredCast/filewizard

File Converter, OCR, Transcription & TTS WebUI

What it solves

File Wizard provides a centralized, self-hosted web interface for performing common file operations that typically require complex command-line tools. It eliminates the need to manually install and configure numerous separate utilities for converting documents, images, audio, and video, or for performing OCR and speech-to-text transcription.

How it works

The application acts as a wrapper around a suite of industry-standard CLI and Python tools. It uses a FastAPI backend and a simple HTML/JS/CSS frontend to allow users to upload files via a browser, select a desired action, and track the progress of the conversion or transcription in real-time. It supports background job processing and can be deployed via Docker for easy setup of all required dependencies (like FFmpeg, Pandoc, and Tesseract).

Who it’s for

It is designed for users who want a private, self-hosted alternative to online file conversion services and those who prefer a graphical interface over the command line for managing file transformations.

Highlights

  • Broad Format Support: Supports over 180 formats out of the box, covering office documents, ebooks, images, audio, and video.
  • AI-Powered Transcription: Integrates faster-whisper for local audio-to-text transcription with optional GPU acceleration.
  • Integrated OCR: Uses Tesseract and ocrmypdf to extract text from images and PDFs across multiple languages.
  • Extensible Architecture: Users can add new conversion tools by modifying a settings.yml file.
  • Secure Deployment: Includes OIDC authentication options and resource limits for child processes to prevent system exhaustion.

Related

  • Project
    aiXander/Realtime_PyAudio_FFT

    A low-latency server that captures live audio and streams processed features like band energies, onset triggers, and BPM to external apps via OSC or WebSockets.

  • Project
    Finrandojin/alexandria-audiobook

    Alexandria is a locally‑run web app that converts a text file (txt/md/epub) into a complete audiobook. It uses an LLM to annotate the book with speaker tags and TTS instructions, then synthesises each line with the built‑in Qwen‑3 TTS engine. Users can pick from nine preset voices, clone a voice from a short sample, fine‑tune voices with LoRA, or generate new voices from textual descriptions. The UI lets you edit the script, batch‑render audio (GPU‑accelerated), and export as MP3, M4B, or per‑speaker WAV tracks for Audacity.

  • Project
    ardha27/AI-Waifu-Vtuber

    An AI-powered VTuber assistant that integrates speech recognition, LLMs, and text-to-speech to create an interactive virtual character for live streaming and personal use.

  • Project
    sooftware/conformer

    A PyTorch implementation of the Conformer architecture that combines CNNs and Transformers to improve speech recognition by capturing both local and global audio dependencies.