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
Nice! Was the product demo created using Velo? ;D
So based on my understanding the input is context and the output is any kind of video, not just product demos but explanatory video for new joiners in a company, to social media content, etc. But what is the quality of the editing and because for explainer videos it can be a generic template format that can apply to any kind of videos but when it comes to product demo or social media content taste and quality and differentiation matter more than just the product voice, as it should not look and feel generic when it comes to such thing. I hope am making my point clear, just curious to know.
Velo
@shekhar_upadhaya_1 Yep, fully made with Velo. We spend a lot of time making the output feel tailored to the context and audience, rather than forcing everything into the same template.
Would love for you to give Velo a try and let us know what you think
I love the idea of grounding videos in company knowledge but documentation changes so fast. When I update a doc in one of the connected tools or through an MCP connector does Velo flag which videos are now out of date? and if there's a way to bulk update existing narrations without starting the prompt process from scratch every time.
Velo
@ryker_rowan1 Yep, Velo knows when the underlying knowledge has changed and asks you to review the video before updating it.
We don't support bulk updates yet, but that's a great suggestion. Added it to our feature requests
Interesting concept you have here! In terms of assets, how does it extract to preserve brand identity throughout the different outputs. As for MCP, if information is being ingested at runtime, what determines consistency
Velo
@omarships Great question!
We extract context from three sources: your knowledge base, connected apps, and MCPs. Brand consistency is then handled through a set of skills that keep the script, visuals, and narration aligned with how your company communicates
Congrats on the launch! When the same topic has conflicting info across sources, like an old Slack thread versus a current doc, how does Velo decide which one to trust when grounding the video?
Velo
@irahimiam Your conversation with the Agent is a big part of it. It helps the agent resolve ambiguity before turning it into a video
Congrats on the launch. The knowledge-grounding angle is the most interesting part to me, especially when the final output is narrated in someone’s own voice. How do you handle review and traceability before a video is published? For example, can a user see which source docs shaped a claim, or flag places where the source material disagrees?
Velo
@yaroslav_stelmakh I personally love this feature. Yes, you can review the generated script with references to the underlying sources, and the agent helps resolve conflicting context before generating the video
The narrate-in-your-own-voice piece is what sells it for me. I keep putting off demo videos for my app because re-recording VO every time I tweak a feature is such a slog. Curious how the cloned voice holds up over a longer script, and whether the localized versions keep your actual voice or swap to a synthetic one per language?
Velo
@lennoxbeflying Thank you!
You can choose either. Localize using your own cloned voice, or switch to one of our public voices. Would love for you to give Velo a try and hear what you think
this is a nice angle on the explainer video problem, most tools make you write the script yourself and then just narrate it. one thing I'm curious about - if I regenerate the same video a week later after tweaking a connector, does it keep the same voice/pacing/avatar so it still feels like the same "presenter," or can regenerating shift the style enough that it feels like a different video?
Velo
@omri_ben_shoham1 Thanks!
You can chat with the agent and tell it exactly how you want to regenerate the video, whether that's preserving the existing style or changing it