Rohan Chaubey

Velo 2.0 - Instantly turn your voice and screen into shareable videos

by
Velo 2.0 is a whole new way to make video messages. It turns raw screen recordings into polished videos and docs, with a chat-native editor, real-time processing, voice cloning, and smart script rewriting. Edit by chatting, not timelines. Record once and get both a video and a doc. Write a script even when there is no audio. Change tone anytime. Everything updates live, so the whole experience feels faster, easier, and more natural.

Add a comment

Replies

Best
Avri Simon

The "edit by chatting, not timelines" approach is the right unlock here. When I was running a 120-person engineering org, the amount of context lost in Slack threads was staggering - someone would spend 30 minutes typing what could've been a 2-minute screen recording. But the reason people defaulted to text was always friction: recording was easy, editing was not. If you've actually made the editing step conversational, that removes the last excuse. Getting both a video and a doc from a single recording is a nice touch too - documentation debt is real.

Sourav Sanyal
@avrisimon this is our exact insight, almost sounds like you were on our retro meeting
Mikhail Prasolov

the chat-native editing is what got me. curious how it handles more complex edits - like if i want to cut a 3-minute section and re-order two others, is that still a conversation or does it get clunky?

congrats!

Sourav Sanyal
@mikhail_prasolov we have super simple editor to handle that for now, you just enable a quick action to enter the editor make your change and your back into chat
Igor Sorokin

what happens when the pdf you're turning into a video has a lot of charts and diagrams? does it describe them, skip them, or try to animate them somehow?

Sourav Sanyal
@igorsorokinua yes it describes all of them. We run a visual model so that we can comprehend everything before making the video
Ajay Kumar

@igorsorokinua It doesn’t skip charts, Velo tries to interpret and explain them as part of the narrative. We use it for research papers internally, made this super quick for you: https://app.usevelo.ai/share/0ffd9297-2258-4414-bfdf-5498fc0c17fb

Super interesting how it turns raw recordings into polished videos with chat based editing and realtime processing how well does it handle multi version content like tailoring the same video for different audiences automatically? BTW, congratulations team for a successful launch.
Ajay Kumar

@hamza_afzal_butt Thanks Hamza! That’s actually one of the strong use cases, you can start with one video and quickly adapt it for different audiences using chat. We’re seeing sales folks use it to customize the same video for different leads all the time

Anusuya Bhuyan
Scree+voice to shareable video is the dream for async teams. How’s the quality on the auto editing side, does it cut the dead air?
Sourav Sanyal

@anusuya_bhuyan You make a voice clone, so even if you have a flight taking off right next to you, your whole voice is re rendered on the video

Ajay Kumar

@anusuya_bhuyan We analyze diction, tone, and emphasis in your voice to automatically refine the video. For silent segments, our AI uses the surrounding context to decide how they should flow

Yash Choudhary

Here again to support for round 2. Cheers, congratulations on shipping improvements so quickly, speaks volumes about the team at Velo.

Sourav Sanyal

@yashchoudhary Thank you so much!!

Ajay Kumar

@yashchoudhary Thanks Yash

Samir Asadov

Chat-native editing on raw screen recordings is a meaningfully better mental model than timeline editing for B2B creators. I produce a finance podcast on the side (the ModeLoop podcast) and the bottleneck is never the conversation — it's the post: trim, intro, captions, clip extraction. Voice cloning + script rewriting could collapse 80% of that into a single chat turn for podcasters who want to repurpose long-form audio into 60s teaser videos. Curious whether Velo handles audio-only sources or strictly screen + voice, and whether the script editor preserves speaker turns?

Sourav Sanyal

 @samir_asadov Screen and voice for now, but this is a super interesting insight for us.

Ajay Kumar

@samir_asadov Great insight, thanks Samir.

Kate Ramakaieva
💡 Bright idea

Congrats on 2.0, team!! The frist time I tried V1 I liked the idea but it felt a bit slow. Really glad to hear the streaming processing was a focus this time around. Going to test this today.

Sourav Sanyal

@kate_ramakaieva Cant wait to hear your feedback, we've also made the entire UX much faster and easier with a chat interface. We're all ears for feedback

Ajay Kumar

@kate_ramakaieva Thanks Kate, do give it a try. Would appreciate your feedback

Jacinto Salz

How does Velo treat the screen recording? Does it do any sort of animation or retouching, or just pure screen capture?

Sourav Sanyal

@jacinto_salz Yup, so this version just focuses on getting the screen right but we do plan to add overlay of code style animation and motion graphics into the same workflow so people could create more engaging videos and along with that on the audio side of things we retouch the whole thing so it sounds like you recorded in a studio.

Aleksandar Blazhev

Congrats on the launch! Just generated a video! Is it possible to edit the video after it's done?

Sourav Sanyal

@byalexai Yup, in the quick actions in the chat there is an option to edit the full editor which gives you access to huge library of editing options.