Koyal turns any audio into end to end cinematic video in one go, with consistent settings, storylines and characters (including you). Unlike working directly with raw models and getting AI video slop, Koyal handles all the complexity agentically so you can focus on your story. You no longer need a camera to create a film.
Most people speak more than they type, and we experience the world in motion, not still images. So while everyone was focused on text-to-image, we asked a simpler question: what if audio becomes the primary interface for creating video?
That idea led to Koyal.
Before this, I bootstrapped a text-to-3D startup working with major game studios (which taught me very quickly why GTA 6 takes a decade). Meanwhile, my sister Gauri left big tech (Instagram video) to research video generation at MIT Media Lab. We realized we had converged on the same niche and did a NeurIPS paper on this.
Koyal is inspired by how Pixar films are made: record the voice first, then craft visuals around emotion and pacing. Instead of hundreds of animators doing that by hand, we built AI systems that translate vocal expression directly into visual storytelling.
And yes, it works for live action too.
This is wild - audio-first filmmaking feels like such a natural next step but no one's really nailed it yet. The consistent character thing alone is huge. Congrats on the launch!
Huge congrats to the Koyal team for solving the painful challenges of video production with such a smart, low friction solution. And great to see it validated by incredible traction with labels like T-Series and Universal Music. Well done team!
Koyal is amazing I loved seeing the Apple Vision Pro ad I thought it was real
Congratulations @agarwalml@agarwal_gauri! Very cool product, looking forward to your future film making successes.
I have worked with Mehul personally on a few projects, and can vouch for his utmost commitment to building a quality product. I'm super glad to see Koyal grow from its earlier stages, to the refined videos it produces now! I'm sure if it follows this trajectory it's gonna produce immense value for filmmakers and content creators.
All the very best, I'm betting on you guys!
Just took a quick look at Koyal and it feels really impressive. I love the Pixar tactic, voice first to build the story and then decide what that looks like! I worked with a Pixar team on a resort project and this was exactly how we approached that concept. Cool to see an app that builds off of that strategy! Assuming Koyal delivers what it promises, I can see myself using this to experiment or iterate without slogging through the manual editing process. Excited to see how the platform grows, especially if they develop even more tools for customizing visual style. Congrats on the PH launch and best of luck!
Hey team, great launch! A suggestion: please put some relevant content on the login page of the app for new users.
Amazing product and very powerful technology! Congrats on the launch.
Are you guys using open source models as part of this? If so, how do you make sure people aren't using your platform to create fake videos of politicians, celebrities, etc.?
Wow — love what Koyal is doing: turning any audio into full cinematic video with consistent characters, dynamic camera moves, and scene logic. Feels like filmmaking meets AI in a very intuitive way. How do you ensure character and visual consistency across long-form videos?
A great tool, exactly thing I need to craft a Christmas message for our team.
Interesting. I got another idea. To create a YouTube video tutorial from the prompts. I usually learn best from the video, but ChatGPT and other tools create only text guidance. What about creating the video guidance?
Still remember the first music video we made using Koyal! Have come so far since then!
Congrats on the launch
