Multi-presenter podcast transcription

For the last six months, I’ve been a presenter on Linux Matters. Prior to that, I spent thirteen years presenting the now-defunct Ubuntu Podcast. Both shows have/had multiple presenters, We record every other week, and send our individual audio files to Joe. He does all the magic post-recording production including editing, audio processing and mastering. That file is then uploaded and eventually makes its way into the Patreon “all episodes” ad-free feed, then to our feed a day or so later. [Read More]

Reading My Own Blog Posts (no bots!)

Download audio I had some fun when I blogged about using a bot to read my blog post. While fun, it wasn’t a particularly pleasant way to consume blog content. The audio is still a bit robotic, with little care for timing, ephasis and stress on words. So in my next blog post, in which I detailed how to setup Mimic 3, I actually read the blog post out loud, recorded that and attached it as an MP3. [Read More]

Setting Up Mimic 3

Download audio Yesterday I blogged about using Mycroft AI’s Mimic 3, an Open Source Text-to-Speech engine I used to generate audio of a blog post. One thing I didn’t mention, which might be useful, is how to setup Mimic 3. It’s pretty straightforward, so here we go. The Mimic 3 developers have some releases over on their mimic3 GitHub repo, which include deb packages. If you want the easy way, maybe use those, but I wanted to try the latest and greatest, so I grabbed the latest master branch. [Read More]

Blog To Speech - In My Voice

Recently my Internet friend Terrence Eden crafted a blog post titled Blog To Speech which you might want to also read. It serves as an inspiration for this post. In short, there’s a trend in blogging (and on some news sites) to add an audio transcription of the page you’re reading, usually at the top of the article. Mostly this is done semi-automatically using a bot to read in an “AI generated” voice such as Amazon Polly. [Read More]