Feature Requests

Serbian has two official scripts: Cyrillic (sr-Cyrl) and Latin (sr-Latn). Currently, Minvo supports only Serbian Cyrillic. However, Serbian Latin is much more widely used in practice (Google, media, social platforms, advertising, etc.), and it is an official script equal by law. Adding Serbian Latin (sr-Latn) would make Minvo much more useful for nearly all Serbian speakers. This is not just “nice to have” – it’s essential for real-world usability. Serbian Latin is already standardized (ISO code sr-Latn) and supported across major systems.

The current AI B-Roll seems to just add 2 media near the beginning of the videos. It's a cool concept but could be way better. Especially for videos that are longer length. I suggest you make it work like this: Ai reads the content. it highlights the key words/topic of each sentence or paragraph. Then based on the topic/keyword of the sentence/paragraph/every 3 sentences, It produces the b-roll and with an option to set a default length. (3 seconds) That way you have B roll all through the videos and it will be ON POINT, not something random! I pretty much do this manually with minivo and its an easy and fast way to get b roll. If we automate the process, OOOOF this will be KING!

Could you please add the Serbian language? Thanks

Right now we can only use the scheduling tool for videos that are made on Minvo.

Love that AI kinda pics an okay-decent for me—would love it we could dial it in even more automatically—but even if it takes human intervention, can you PLEASE PLEASE PRETTY PLEASE have at least some: x, y, cordinates we can change the values with the scale ability (like other areas in the app already do) for framing? This is kind of a big deal as far as the clip is concerned and we're leaving pretty good amount of the chance with the mouse... I have a CORSAIR DARK CORE RGB with a custom 18,000 DPI optical sensor optimized for precision details in professional high end video, audio, and image applications... ...and I just had anxiety trying to shrink and enlarge the frame to be: "lower down" than its too low, now you can see the box that was on screen, now its just the guests eye. Again, would love to train the AI to know "have eyes balanced in top 1/3, don't have ANY white box that the guest was in showing, auto-scale to whatever size is best needed, then center horizontal and vertical. If however, it never gets to that point i don't want to be feeling excited about how cool the 40+ clips are, the brand theme with our colors and perfect font, the minimal even typos that barely exist only to need 5 mins HOPEFULLY to get the scaling right of the framing box that in a best case scenario is 90% luck with 10% guessing. Love the app overall, you guys nailed 95-97% of things, truly. Well done on the 400 yard drive. Would love to see it get to 100% for the last 15-foot putt on less than a handful of items, this being one of them. ~Rooting for your apps continued success (Just upgraded to Pro btw, and very close to upgrading at least a few more times to higher monthly hour plans....help make this a no brainer for me please) PS - another main one is the into/brand image/thumbnail - don't love that no matter what goes in applies to everything else from there on out, its unusable in its current form. PSS - ability to "Cut" the timeline, not just hope theres a word and cut that section, but move the cursor and know from 9 secs and 32 secs in all the way back to the begining its gone, outta there, done.

Unlike the framing, captions remain at one position for the whole clip; but sometimes you have to move it only certain sections of the whole clip. As you would do cuts and adjust the framing, the position of the Caption should respect the the cuts and move only within one cut, not for the whole clip!

As a user, I would like to be able to apply a specific recipe (clip template) to all the clips. For example, produce ready-made vertical clips from horizontal video.

Inputs: upload a folder of b-roll, Specify edit length AI: cut the most interesting clips of interest from the provided footage. Maybe have a few parameters to search for along with custom keywords... Parameters: smooth motion, smiles, etc. keywords: "scoring a goal" Outputs: -download all clips stitched together as one clip -download a zip of the individual clips -bonus points, download an xml file for resolve, premiere, or rcp that uses the original footage names that can then be relinked!

Allow MCP connections to let AI agent control Minvo's main features

once a cut is set you cannot undo this, that's a pitty however!