
ngram
Video agent for product and marketing teams
504 followers
Video agent for product and marketing teams
504 followers
Product updates deserve better than text-only changelogs, expensive agency cycles, or generic AI slop. ngram’s AI video agent turns release notes, specs, screenshots, docs, URLs, and product recordings into polished, on-brand videos for launches, demos, onboarding, support, sales, and social. It plans the message, writes the script, builds the storyboard, creates visual variants, and helps teams communicate every product story clearly.
This is the 2nd launch from ngram. View more
ngram 2.0
Launched this week
Turn ideas, documents, and recordings into narrated videos. ngram analyzes uploaded videos and screen recordings to identify key moments and build clear product walkthroughs. Create animated explainers or add an AI avatar presenter, then refine your video in chat.









Free Options
Launch Team / Built With

Dropbox SignSimple, secure eSignatures for the way your team works.
Promoted



worth trying out. Congrats on the launch!
@ramitkoul Thanks, Ramit! Would love to hear how it goes when you try it, especially anything that feels unclear or takes more effort than it should. You can also tag 'askngram' on a text-heavy thread on X/twitter, and it’ll turn the thread into an explainer video.
@ramitkoul Thank you Ramit!
@devadutta Congratulations. And happy product launch.
@devadutta @huisong_li Thank you, Huisong! Really appreciate you stopping by and supporting the team 🙌
You can also tag 'askngram' on a text-heavy thread on X/twitter, and it’ll turn the thread into an explainer video.
Congratulations on 2.0. I am preparing a launch video myself at the moment, so this is close to home. The part I find hardest is deciding what the script leaves out, more than the visuals. When ngram plans the message from release notes, does it ask who the video is for before it writes, or does it work the audience out from the material?
@kaosar Thanks, Kaosar! You can specify the audience in your starting brief alongside the release notes, so it guides the script from the beginning.
For example: “For existing customers, focus on what changes in their workflow and skip the implementation details.” I’d make that explicit rather than rely on the material alone to communicate who’s watching. And I agree: deciding what to leave out is often the hardest part.
You can also tag “askngram” on a text-heavy thread on X/Twitter, and it’ll turn the thread into an explainer video.
@ranjanrishikesh Thanks, Rishikesh, that's clear. Putting the audience in the brief is what I'd want to do anyway, so it's good to know the script follows it from the start. Good luck with 2.0.
The success depends completely on how fast the API responds and how long it takes to show the results when making things at once. Making the part automatic lowers costs a lot but how much it costs each minute will decide if this works for a lot of support documentation changes.
@sundas_tariq Agreed, Sundas. For regular documentation updates, the time until the finished video is ready and the cost per usable minute both matter. Our API runs generation asynchronously and can notify your system through a completion webhook. It also supports a credit estimate before generation; usage depends on the model, video duration, and whether you add a presenter.
I wouldn’t quote a batch turnaround time without testing the workload. Roughly how many videos would you need to update, and how long would each be?
You can also tag “askngram” on a text-heavy thread on X/Twitter, and it’ll turn the thread into an explainer video.