The AI video suite: from topic to rendered faceless video
By The Growvo Team
Short-form video is where distribution lives right now, and it is also where most small teams stall: scripting, recording, editing, and captioning a single clip can eat an afternoon. The Growvo video suite collapses that into two steps — describe the topic, review the storyboard, render.
Storyboard first, render second
Give the planner a topic and a scene count (1–12) and it writes a scene-by-scene storyboard: narration, visual direction, and timing for each beat. Nothing renders until you say so — you can edit scenes, regenerate the ones you don’t like, and only then enqueue the MP4 with an AI voiceover. That split keeps iteration cheap: planning costs one AI generation, rendering costs a second.
The same suite, over the API
Everything the video tab does, POST /v1/videos does too. Plan a storyboard from your own pipeline, or pass render: true to plan and enqueue the MP4 in a single call, then poll until it is ready.
curl -X POST -H "Authorization: Bearer REDACTED" \
-H "Content-Type: application/json" \
-d '{"topic":"3 growth loops for SaaS","sceneCount":5}' \
https://api.growvo.ai/v1/videosBuilt to be published, not downloaded
- Rendered videos land in your media library, ready to attach to any post.
- Publish the result to TikTok, YouTube, Instagram, and the rest of the 13-network pipeline without leaving the app.
- Bring your own provider keys and generation stays uncapped on that provider.
The suite sits next to AI images and the carousel builder, so a single idea can ship as a video, a carousel, and a thread — each tuned to its network. That is the whole point: one input, every format your audience actually watches.