Desktop applications and open-source tools for AI, voice cloning, and text processing.
Built for Apple Silicon with privacy-first design.
Voice Cloning & TTS for macOS
Clone any voice from just 3 seconds of audio. Local-first voice cloning, text-to-speech, PDF reader, and audiobook creator with four TTS engines, optimised for Apple Silicon.
Production-ready infrastructure for AI workloads.
OpenAI-compatible local inference on vLLM with LMCache, tuned for RTX 5090, plus developer tooling and scripts for fast iteration.
GitHub RepositoryProduction pipeline for converting PDFs and images to searchable text/JSON with parallel processing and robust retry/logging.
GitHub RepositoryReach out for support, feature requests, or collaboration opportunities.