Spira Maxima - Video model that turns script into viral social media videos
by•
Spira Maxima turns plain text into a finished social video: presenter, on-trend B-roll, captions and music in one pass, ready to post with nothing to re-edit. Bring a photo and voice for your AI clone, product shots, or a recording, and it builds the edit around you. Post-trained on social trend and performance data, so every video follows what is working to maximize your social impact.
Replies
I have worked with multiple content based saas companies. And I am honestly impressed by the quality you have shown in the video. Will give it a try for sure. Good luck with the launch.
@lakshya_singh Thank you a lot, man. We will definitely keep it up.
The part that got me was the B-roll. It cut in shots that matched the words, not generic city timelapses. Whoever trained the taste in this model did a good job.
@jackruirui thanks!!
Will it tell me no? Like if my script is boring, does it just make a boring video with nice B-roll, or does it push back?
@carlvert I have a built-in Script Enhancer, so even if you only type a word or two, it can flesh out the organic sentence for you. You should give it a try.
TikTok and Instagram are both getting better at detecting AI content. Are you seeing any reach penalty on videos made this way, or is "on trend" enough to beat the filter?
@alexia_li We are delivering great results for our clients. They include companies listed on Nasdaq and backed by YC and top tier venture firms in Silicon Valley. I think the logic behind it isn't whether the content itself is made by AI, but whether it genuinely delivers value to the audience and can spark their interest and engagement.
Can I feed it a script in one language and get the presenter speaking another???
How long does it usually take to go from an idea to a finished video? Congrats !
Agreed that finishing is the wall, but in our own social video the last mile wasn't the edit, it was legibility. On-screen text that looks fine in a preview is unreadable at the size people actually watch, and we ended up switching to designed graphics over generated ones for exactly that reason. If Maxima is placing captions and product shots itself, I'd want to see it at phone size mid feed scroll before I believed nothing left to edit.
@asadmalik901 Of course. Before launch, we ran extensive internal testing, and to our pleasant surprise, our generation success rate exceeds 95 percent, putting us ahead of the vast majority of models on the market. Try it out and share your feedback with us.
@llma Generation success rate isn't the number I was asking about. A clip can complete fine and still ship captions nobody can read at phone size, those are two different failures. If you have a number on the second one, like how often on-screen text stays legible mid feed scroll on a 6 inch screen, that's the one that would get me to try it.
The trend detection part caught my attention. Knowing what is starting to work before creating content around it could be really useful for social teams.
@shameka_fabros Thanks, Shameka! That’s a big part of why we post-trained Maxima on social trend and performance data. We want that to show up in the finished video, from the B-roll to the captions and pacing. Really appreciate the support :)
Building the whole social video from a script in one pass, presenter, b roll, captions and music, is a big time saver since editing is usually where these tools stop short. Using a photo and voice to make an AI clone of yourself is a clever touch. Curious how much control you get over the B roll choices before it renders.
building the edit around your own product shots is the useful bit. can you lock those shots so a regeneration changes the pacing without changing what the product looks like?