Following on from my previous TTS post using Chatterbox Turbo (or any other TTS like Kokoro or Qwen3-TTT), here is code to combine audio files in a single .m4b audiobook retaining author and title metadata, chapter markers, and a cover image. Mostly this is a Python wrapper to FFmpeg.

In my last post, I tried Qwen3-TTS... This time, I test Chatterbox Turbo by Resemble.ai, which is an open-source, MIT licensed, text-to-speech model with zero-shot cloning.

Alibaba’s Qwen3-TTS for Speech Synthesis (text-to-speech) was open-sourced (Apache-2.0) on 22 Jan 2026. And within the last couple of weeks, we now have Apple Silicon optimization via MLX-Audio. Here is code to create an audiobook from an ePub.

In March 2025, I posted an opinion piece entitled “My Disillusionment with Generative AI”. Things have gotten worse since then, to the extent that “Slop” and “AI Slop” have been picked as the Word(s) of the Year for 2025. What follows are my thoughts on the trajectory of technology and, more specifically, AI, as reflected in the Word(s) of the Year (WOTY).

The current version of CrossOver 25.1.1 utilizes with Apple’s Game Porting Toolkit 2.1. Here is how to update it to use Game Porting Toolkit 3.0 (GPTK), released (updated) on 5 December 2025, which emulates NVIDIA DLSS with MetalFX!

In my last post, I described trying out Kokoro text-to-speech (TTS) model via Kokoro-FastAPI web UI in a macOS (native) container. Here, I install Kokoro-TTS and Abogen on Windows, to take advantage of my Nvidia GPU.