Directly Transcribed

While writing this blog, I would like to be able to create a workflow that allows me to quickly create posts written in my own voice and post them to the site without a lot of effort. One of the things that causes a lot of effort to take place is having to type out every single word. These days, it’s pretty easy to use a microphone to record new spoken content and have it transcribed into something that can be posted online. I’ve recently been experimenting with a tool called AudioPen, which records my voice, transcribes it, and then submits it to an AI model to rewrite the content a bit. This is particularly interesting because if you’ve ever recorded yourself speaking live and listened back to it, you’ll note that you make a lot of mistakes, the grammar isn’t necessarily correct, and what you generally hear is pretty forgivable if you’re a listener, but not very forgivable if you are a reader of that transcribed text. I really wouldn’t want to publish directly transcribed text to the website without a significant amount of editing, and so it’s nice that it sends it through this AI model, which corrects some of the grammar and enhances some of the wording to really get at the meaning. Unfortunately, the prompt that AudioPen uses is a little more aggressive than I would like and removes a lot of what makes my voice hear, at least my written voice, sound like me. I tend to sound more like an AI model, so I’ve been playing with some other tools to hopefully make this as easy of a workflow, but with less loss of fidelity in the transcription.

Processed fully via superwhisper, using custom prompt to GPT-4 Turbo

I’ve been exploring a workflow that enables me to quickly generate posts in my own voice with minimal effort. One of the biggest challenges is the need to type out every single word. Nowadays, it’s fairly straightforward to record spoken content with a microphone and have it transcribed for online posting. I’ve been experimenting with a tool called AudioPen, which records my voice, transcribes the content, and then enhances it through an AI model. This approach is particularly fascinating because, as many of us might have noticed, live speech often includes numerous mistakes. The grammar might not be on point, and while these errors are generally forgivable to listeners, they are less so to readers of the transcribed text.

Directly publishing transcribed text without considerable editing wouldn’t meet my standards. Hence, the appeal of AudioPen’s method of running the content through an AI model to correct grammatical errors and improve the wording to capture the intended meaning more accurately. However, the prompts used by AudioPen tend to be more aggressive than I’d prefer, stripping away much of what makes my voice uniquely mine. As a result, my writing ends up sounding more like it was generated by an AI model than me. Therefore, I’ve been experimenting with other tools, aiming for a workflow that is just as effortless but retains more of my personal touch in the transcription.

Transcribed via superwhiser, pasted into GPT-4 playground with prompt

While writing this blog, I’d like to create a workflow that makes it easy for me to quickly generate posts in my own voice and post them to my site without much effort. One of the main challenges is the need to type out every word. These days, using a microphone to record spoken content and transcribe it into text for online posting is fairly straightforward. I’ve been experimenting with a tool called AudioPen, which records my voice, transcribes it, and then feeds it into an AI model for a bit of rewriting. This process is interesting because if you’ve ever recorded yourself speaking and listened back, you’ll notice many mistakes. The grammar isn’t always right, and even though what you say might be forgivable to a listener, it’s often not as forgivable to a reader.

I wouldn’t want to publish directly transcribed text to my website without a significant amount of editing. It’s beneficial that the tool uses an AI model to correct grammar and enhance wording to better capture the meaning. However, the editing by AudioPen is a bit more aggressive than I’d like, removing much of what makes my voice, or at least my written voice, sound like me. I end up sounding more like an AI model. So, I’ve been exploring other tools to achieve an easier workflow without losing the authenticity of my transcription.

Audiopen

In writing this blog, my aim is to establish a workflow for swiftly crafting posts in my own voice with minimal effort. One factor that often requires considerable effort is typing out every word. Nowadays, it’s relatively simple to record spoken content using a microphone and have it transcribed for online posting. I’ve been exploring a tool called AudioPen, which not only records and transcribes my voice but also submits the content to an AI model for rewriting.

This feature is intriguing because anyone who has listened to their own live recordings knows that mistakes are common. While these errors might be forgivable for listeners, they are less so for readers of the transcribed text. Directly publishing such content without substantial editing would be unwise. Thankfully, AudioPen’s AI model rectifies some grammatical issues and refines the wording to convey the intended meaning more effectively.

However, AudioPen’s prompt tends to be somewhat aggressive, stripping away elements that make my written voice unique and causing it to resemble an AI-generated text. Consequently, I’ve been experimenting with other tools to streamline the workflow while maintaining greater fidelity in the transcription process.