Velo turns your raw screen recordings into watch-worthy, ready-to-share videos with AI. In seconds.
This is the 3rd launch from Velo. View more
Velo 3.0
Launched this week
Velo 3.0 is here, our third and biggest launch yet.
Start with a screen recording or a prompt. Describe the video you need, and Velo writes the script, narrates it in your own voice, and builds the finished cut. It stays grounded in your company knowledge, from your docs and tools you connect through connectors and MCP. Edit by typing changes. Localize the finished video into 25+ languages in one click.
Recording or prompt, Velo turns either into a polished video you can ship anywhere.
Free Options
Launch Team / Built With
Velo
Hi Product Hunt! 👋
I'm Ajay, CTO and co-founder of Velo.
When we started building Velo, we thought the challenge was making it easier to create work videos.
As we worked with more teams, we realized that wasn't the real bottleneck.
The hardest part wasn't creating the video, it was finding the right knowledge to put into it.
The context behind every product demo, onboarding guide, support reply, or training video already exists somewhere. It's just scattered across docs, help centers, Slack, Teams, tickets, and conversations.
That's what led us to build Velo 3.0
✨ What's new:
Simply describe what you want to explain and Velo finds the right company knowledge, grounds itself in that context and turns it into a polished video
We taught every Velo to speak 37 languages, so the same explanation can reach teams and customers anywhere
This launch is a big step toward what we believe the future of workplace video looks like: not just creating videos faster, but making company knowledge instantly explainable.
We're excited to hear what you think, answer your questions, and learn from your feedback throughout the day. Thanks for stopping by! 🚀
Try for free: usevelo.ai
Velo
@ajaykumar1018 Super excited about this launch
@ajaykumar1018 Congrats on the launch! Quick question: what's the smartest way you’ve seen teams organize or tag their scattered knowledge so Velo can surface the most accurate, up-to-date context; and do you recommend any small, practical changes teams can make today to improve Velo’s results?
Velo
@swati_paliwal Honestly, keeping docs up to date matters far more than organizing them perfectly. The better the source of truth, the better Velo's output
@Velo keeps surprising me, just when I think they’ve nailed it, they ship something new and impressive. Many congrats Sourav, Ajay, Grege and team. :)
A fellow hunter and friend, told me yesterday, Velo was one of his favorite products last month, and I couldn’t agree more.
Though Velo was robbed off from the top spot on the leaderboard today, that doesn’t diminish the huge amount of love and support they’ve earned from the community launch after launch. The leadership at PH had communicated, the most valuable launches are those that keep shipping and launching fast. Velo is definitely one of the most interesting launches I always look forward to.
I use Velo personally, my team uses it, and our community does too... we all love it. With every release they push the boundaries: the latest update can pull from your company knowledge to generate videos from a prompt and now supports multiple languages.
If you haven’t tried Velo yet, give it a go: https://usevelo.ai/
The knowledge-grounding piece is wow. Anyone can generate a clip. Knowing which of a company's scattered docs is the true one is the hard part. Wondering...a help doc, a Slack thread and a support ticket usually say three slightly different things about the same feature. When you guys write the script, does it pick a winning source or flag the disagreement before it narrates something confidently wrong?
Velo
@artstavenka1 It asks you and looks at the entire time series of all events
Velo
@artstavenka1 @sourav_sanyal The conversation is a big part of it, it helps the agent frame the right story
Prompt-to-video honestly sounds more useful than recording first for products that change every week. BTW, do you support voice based edits or we have to type the edits?
Velo
@zerotox Only text for now
Would love to see a way to trim or cut specific sections before sharing, like removing those awkward pauses or the bit where I fumbled through a tab. Right now it feels like I have to either take the whole thing as-is or edit elsewhere first.
Velo
@c_oglu86713 Curious, we actually let you pause on our recorder. Would love for you to try it feedback
Velo
@c_oglu86713 We actually support this today! Would love to hear how it works for your use case.
The agent understands what's happening on your screen, what you're saying, and your speaking style, then edits the video for you
Shadow
We started using Velo at Shadow back in 1.0, mostly because making demo videos for clients was such a pain.
You'd record something, then spend an hour cutting it down. Velo turned that hour into a few minutes.
By 2.0 the voice cloning was good enough that clients couldn't tell it wasn't us talking.
The new version is a bigger deal than it sounds.
Prompt-to-video means you describe the walkthrough instead of recording it, and because Velo now knows our product, it fills in the rest.
The interesting part isn't that it's faster. It's that anyone on the team can make these now, not just the one person who was good at it. That changes how many we can make.
Nice work. Curious to see where it goes. Congrats to the team!
Velo
@hersh_singh This warms my heart
Velo
@hersh_singh This made my day ❤️, thanks for sticking with us and sharing your experience
How do you handle varying audio quality in the input recordings, and is there a way to adjust or fine-tune the AI's editing decisions?
Velo
@aymnart You could do your own voice clone and edit every single word the AI generates in the edit script. On the prompt side of things you can just direct it however you want it to be
Velo
@aymnart Yep, you can edit every word yourself or let AI Rewrite do it in different personality styles
the "grounds itself in your company knowledge" part is the interesting bet here, most video tools just take what you type or record at face value. question about that: once a video's generated from your docs/connectors, what happens when the source doc changes afterward, does the video get flagged as possibly stale, or is it a snapshot that's accurate as of generation time and then just quietly drifts from the source over time?
Velo
@galdayan Today, it’s a snapshot accurate at generation time. The sources stay attached for traceability. We’re building source-aware freshness so when a connected doc changes, Velo can flag the affected video and update only the relevant sections.
Velo
@galdayan Right now, it's more of a snapshot at generation time, but regenerating pulls in the latest context from all your connected sources
@ajaykumar1018 makes sense, and good to see Sourav mention the flagging/partial-update piece is already on the roadmap. that's honestly the harder problem to get right, most tools would just leave it as a silent snapshot forever