I began work on Project Questa on the 27th of September, because I couldn’t get Khazad Voice TTS to work on my PC. Since then I’ve spent several days a week working on my AI narrator utility and have made steady progress. Last time I wrote about the project the production pipeline ran as follows. DXCam, OpenCV, Windows OCR and Microsoft Speech API (SAPI). Over time, I determined that Tesseract was a better OCR and that Kokoro TTS produced superior narration. However, in the last week I found that constant fine tuning across different aspects of the production process was not really producing any significant improvements. The main problems were capturing text from dialogue windows that required scrolling, as well as overall latency in producing narration. A delay over 5 seconds is too long in my assessment. Hence I decided to fundamentally change the overall approach to dialogue capture.

A few years ago, there was a fan created project to provide voice narration of NPC dialogue in the MMORPG, The Lord of the Rings Online. This mainly involved capturing the text in the quest dialogue windows and then sending it to OCR software, before using a text-to-speech program to read it. LOTROVoice as it was known, broadly worked but the creator stopped developing it as it proved troublesome to maintain. However, I recently discovered Khazad Voice TTS which is a separate project that does pretty much the same. I went so far as to install this “immersive AI narrator for LOTRO” after seeing a YouTube video of it being used successfully. Sadly I ran into issues configuring Khazad Voice TTS, because I have two monitors and LOTRO runs on the secondary (by my choice) and not the primary. I couldn’t “lasso” the dialogue windows in LOTRO during the calibration set up, which effectively prevented me from completing the process.