Picks and shovels

Hello everyone!

I’d like to share an audio narration of my story and explain why, in some cases, I make a narration instead of a film.

Some stories, like this one, simply aren’t very cinematic. There aren’t many moving parts. The process is psychological — more internal than external.

A film requires far more time and effort. First, the story has to be distilled into a screenplay. Then comes the long struggle with the video generator, which only produces five-second clips. To create a four-minute video, you need around eighty five-second segments. Those clips then have to be stitched together while making sure the characters’ appearance doesn’t change from shot to shot, and while constantly preventing the generator from exercising the strange kind of “creative independence” it tends toward. And that’s only part of the production cycle.

Finally, there’s the logistical problem. Some time ago, I bought high-quality voices on ElevenLabs at a very good price. These voices are far better than the ones provided by the video generators themselves. They can convey subtle nuances of speech and allow fine control over intonation, tone, and delivery. However, the problem with using these voices is that the characters’ lip movements are not synchronized. There are services that specialize specifically in lip-syncing, but using those tools is very expensive. At the moment, it’s simply beyond my means.

So even in the previous mermaid video, I had to decide what I was willing to sacrifice.

At the same time, ElevenLabs has a policy where, after you accumulate a certain number of audio credits, they no longer roll over into the next month. So for me, it makes more sense to use them on narrated stories rather than simply watch them disappear.

That voice platform also offers its own synchronization tools and a more advanced video generator. The time will come when I’ll learn and use all of that. But it’s expensive, and for now, that time hasn’t arrived yet. )