The thrilling conclusion: Mandarin for Beginners is live

As you may recall from several previous posts, I've been working on creating audio recordings of beginner Mandarin lessons for English speakers using text-to-speech (TTS) technology. I used OpenAI's TTS model, which handles both English and Mandarin well, and also tried ElevenLabs, which offers many voice

Further adventures with TTS models reveal serious limitations

It was a good morning. The sun was peeking over the horizon. I had a steaming mug of coffee, and my MacOS scripting-and-voiceover app was behaving as expected. I'd even added voices from the ElevenLabs text-to-speech (TTS) model by adapting this Swift package. While it doesn't

Debugging the spelling bee GPT

My eleven-year-old daughter is hard-core into spelling and has ambitious to qualify for the Scripps National Spelling Bee. So far, she's won multiple school bees and made it to second place in her most recent County bee. To prepare, she's been using Scripps' Word Club

Building a macOS app for AI-powered script creation and voiceover recording

Remember my quest to create Mandarin lessons for beginners and record them with AI? I wanted to use a OpenAI's GPT-4 model to generate the lessons and then record them with AI voices from OpenAI and ElevenLabs. How hard could it be? Spoiler alert: It was actually pretty

APIs the lazy way

I'm still tinkering with my voiceover scripting and recording app. I've made some decent progress, and now I can easily choose from all of OpenAi's six voices when playing audio or saving it an MP3 file. I also took a shortcut by using AI

Wrestling with TTS and GPTs

After some long conversations with my Mandarin for Beginners GPT, I decided that allowing it to improvise lessons and deliver them through voice chat was not the best approach. Users could easily burn through their 40 messages per three hours just with some basic pronunciation and conversation practice. I know

My very strict language tutor GPT

I love the idea of learning and speaking other languages, but my enthusiasm exceeds my ability. While I can manage small talk in French and Spanish, my attempt to learn Mandarin ended with dropping the class to preserve my GPA. So, of course, I am trying to build an infinitely

Building a gratitude bot with ChatGPT and Zapier AI Actions

I know I should send more thank you notes, perhaps even a lot more thank you notes, but I'm not good at warm and engaging prose. I end up staring at the screen, worried that my email missives will seem too cold, awkward, or lame. But ChatGPT is

Using custom GPTs to decipher SwiftUI packages

I am fairly new to SwiftUI and often make use of packages I find on GitHub. But understanding how these packages work and how best to use them can be rather time-consuming. In fact, the other day I was struggling to integrate a SwiftUI app with an OpenAI Assistant. Fortunately,

Photorealistic vs. photo

Update: Since I wrote this post, I've been thinking about the ethical implications of AI-generated art. Lately, I've trained models on digital art I created myself, incorporating their generations into this blog. Most recently, I've been using Tess to source artist-friendly AI-generated imagery. Is

Fire should not be hair.

Update: Since I wrote this post, I've been thinking about the ethical implications of AI-generated art. Lately, I've trained models on digital art I created myself and incorporating their generations into this blog. Most recently, I started using Tess for artist-friendly AI images. Since this blog