Social Cutdowns
Ask for a vertical clip built for TikTok, Reels, or Shorts and your employee renders it in the right shape from the start, with sound, ready to post without any reformatting.
Video
Hand your employee a prompt and get back a short, ready-to-post video clip, filed straight into your Drive. Built for social cuts, ad concepts, and quick product demos. Editing your own footage is coming next.
Describe the clip you need, a product demo, a social teaser, an ad concept, and your employee generates it from the prompt alone. No footage to shoot, no editing timeline to learn, no separate tool to sign into. The finished video lands directly in the employee's Drive, ready to download or hand off.
Every clip runs 4, 6, or 8 seconds, picked up front rather than trimmed after the fact. That's short by design: the length that fits a social feed or a quick product walkthrough, not a full production pipeline, so a prompt alone is enough to get something usable back.
Pick the model behind the generation the same way you pick the model for chat, faster and cheaper for a quick draft, higher fidelity when the clip is actually going out the door. The default is Google's Veo 3.1 Standard; Veo 3.1 Fast trades some polish for a lower per-second cost, and ByteDance's Seedance 2.0 Fast is the cheapest of the three but always renders without sound. Set the default engine once in the tool's settings and every clip after that uses it unless you ask for something different.
What makes this a real workflow tool rather than a novelty toy is that it's an AI employee capability, not a standalone app you jump to. Ask an AI employee for a finished marketing task, caption, video, and hashtags together, and the video comes back as part of that same conversation, no separate tool to open, sign into, or learn.
Because a clip costs real money per second, it's only billed once generation actually succeeds, a failed render never shows up as a charge, and the credit check that guards the spend runs before the clip is generated, not after.
From Prompt to Posted
Ask for the clip in plain English, "a 10-second product teaser with our logo at the end", and the employee generates it, no timeline editor, no rendering settings to configure. What comes back is the finished file, not a project to keep working on.
Because it's an employee tool like any other, it fits into a real workflow: ask for the clip as part of a broader task ("write the caption and generate a teaser video for this launch") and both come back together.
Built for Short-Form, Not a Production Suite
This isn't trying to replace a video editor for long-form work. It's built for the clips that actually get posted every day: a product teaser, a quick explainer, a social ad concept, 4 to 8 seconds long. That focus is what makes a prompt alone enough to get a usable result.
Every generated clip is filed straight into the employee's Drive next to whatever else it produced that day, so a marketing task's output stays together instead of scattering across separate tools and downloads folders.
Engines, Sound, and Cost
Three engines are available: Veo 3.1 Standard and Veo 3.1 Fast from Google, and Seedance 2.0 Fast from ByteDance. Standard is the default and priced for the highest fidelity; Fast costs less per second at slightly lower polish; Seedance is the cheapest of the three but has no native audio option, so it always renders silent.
Sound is on by default on the two Veo engines and costs more per second than a silent render, so switch it off when the clip will be muted, looped, or scored separately later. Whichever engine and audio setting you leave as the default lives in this tool's settings, so the employee uses it automatically and you're only asked when you request something different for one clip.
How It Works
One prompt in, one finished clip back, filed and ready
Your employee reads your request, pulls out the subject, the vibe, the length, and the format from what you said and from where you told it the clip is going, then it proposes a one-line plan (shape, length, sound on or off, the gist) before it renders. That line is your chance to redirect before any money is spent.
Because each clip costs real money per second, it checks your remaining credit balance before it calls the video engine, and refuses to spend if the balance won't cover it, so you never get a surprise charge for a clip you couldn't actually afford.
Once generated, the clip is pulled off the video engine's servers and re-hosted on your own storage, filed automatically into Drive, and a working link is pasted straight into your employee's reply so you can watch it without hunting for it. If a clip isn't quite right, just ask for another; regenerating is normal and cheap relative to a full production pipeline.
Every clip renders at 720p and 16:9 or 9:16 to keep cost and turnaround reasonable. If a clip needs a different look or a longer run, tell your employee directly; it will regenerate with your new direction rather than trying to edit the existing file.
Use Cases
Quick Ad Concepts
Describe the product moment you want and get a short landscape or vertical clip back to test as an ad creative, before you commit to a full production shoot.
Product Demo Beats
Turn a feature description into a short visual beat for a landing page, a pitch deck, or a launch post, generated on the spot instead of waiting on a video editor.
FAQ
Can I edit my own footage instead of generating from scratch?
Not yet, today's tool generates from a text prompt. Editing uploaded footage is on the roadmap.
Which video engines can I pick from?
Three: Veo 3.1 Standard (the default) and Veo 3.1 Fast, both from Google, and Seedance 2.0 Fast from ByteDance. Fast and Seedance cost less per second than Standard; Seedance always renders without sound.
Where do generated videos go?
Straight into the requesting employee's Drive, the same place all its other work product lands.
Which plans include video generation?
Starter and above. It's not included on the Free plan.
Exactly how long can a clip be?
4, 6, or 8 seconds, picked before generation starts. There's no option to render longer or to trim it afterward inside the tool.
Can I ask for a video as part of a bigger task?
Yes. Ask an employee for a caption and a teaser video together and both come back in the same conversation.
Am I charged if a generation fails?
No. A clip is only billed after it renders successfully, so a failed attempt costs nothing.
Is there content the tool won't generate?
Yes. It refuses nudity, sexual content, gore, graphic violence, hateful symbols, and real people's likenesses without basis, and declines indirect attempts to get around those limits.
Where Video fits
Video is part of Things they can do out of the box.
Every AI employee ships with built-in abilities that work out of the box. Search the live web for real-time information, scrape and crawl any website for structured data, and generate images directly in conversation. No plugins to install, no APIs to configure.
- Things they can do out of the box: Research, create, and extract without plugins.
Read the guide
More in Capabilities
- Web Search: Every AI employee can search the live internet for current information and answer with sources, no setup required. It runs automatically whenever the employee needs something it does not already know, such as a competitor update, a price, or a recent news item. Results are cited titles, snippets, and URLs, synthesized into a plain answer inside the chat.
- Web Scraping: Give any employee a URL and they read the full page: article, blog post, documentation, competitor page, pricing table, whatever is public. They return clean text with the ads, navigation, and boilerplate stripped out, ready to summarize, compare, or act on. It is enabled for every employee at hire, costs no credits, and works on JavaScript-heavy pages without any setup on your side.
- Image Generation: Ask any employee to create an image and it builds a detailed prompt, generates it with an OpenAI image model, and saves the result to Drive with a persistent link. Use it for logos, social graphics, illustrations, diagrams, or landing page visuals, described in plain language. No setup required: every employee can generate images at hire, with a Model, Quality, and Shape default you can adjust per tool.
- Code Interpreter: Code Interpreter is on our roadmap: a sandboxed Python environment your AI employee will use to run scripts, crunch numbers, and transform data files on request. Instead of describing a calculation in words, you'll be able to ask for the actual computation and get back a checked result, not a guess. It is not available yet.
- B2B Marketplace: A network of real, vetted businesses living inside Sistava. Ask any AI employee to find a vendor, a partner, or a service provider, and it checks this network first, before it ever touches the open internet. Get listed yourself and the same network works the other way: visitors, customers, and other businesses' AI employees can discover and recommend you.
- Document Editor: Ask an employee for a spreadsheet, a report, a slide deck, or a data export, and get back a real .xlsx, .docx, .pptx, .csv, or .pdf file, not a wall of text pasted into chat. It can also revise a file you already gave it through the same chat-and-Drive workflow, keeping the work you did not ask to change intact whenever the format supports it. For PowerPoint, it can turn a brief into native slides with layouts, charts, images, shapes, tables, and speaker notes. PDFs can be polished reports or colorful, fully designed pages with professional print typography. Included with every employee on every plan, nothing extra to connect or unlock.
- Premium Prospect Database: Find real people to sell to and reveal their verified work email and phone, pulled from a premium database of over a billion professionals worldwide. Filter by role, seniority, industry, company size, and location to build a targeted list, then have your employee save the best prospects straight into your CRM. A premium add-on on paid plans; on the free plan your employee researches prospects on the open web.
- Send an Employee to Your Meeting: Share a Google Meet, Zoom, or Microsoft Teams link and your employee joins the call as a named participant. It listens, keeps a full speaker-tagged transcript, and speaks up out loud when you address it by name. When the call ends, the transcript lands in Drive and a summary shows up in chat.
- Get a Live Meeting Transcript: Your AI employee joins a Google Meet, Zoom, or Microsoft Teams call and captures a full transcript as people speak, tagged by speaker and timestamped. Ask for it mid-call, ask for it after, or just ask what someone said ten minutes ago. When the meeting ends the transcript is saved to your employee's Drive automatically.
- Meeting Summary: When a meeting your employee attended ends, it writes a summary and drops it in chat automatically: what got decided, who owns what, and the action items. No need to ask for a recap, it is already waiting when you check in.
- Document Text Extraction: When you attach a document to a chat message or upload it for training, your employee turns it into readable text on its own. PDFs, Word, Excel, and PowerPoint files, OpenDocument files, RTF, and plain text or data files all come through automatically, tables included, with no conversion step for you to run first.
- Import a Skill from GitHub or a URL: Paste a link to a GitHub repository or a URL that hosts an Anthropic-style Skill package, and your employee will import the whole thing directly instead of you rebuilding it by hand in the Create Skill drawer. This is on our roadmap and is not active yet: the option appears in the Skills toolbar and in the Create Skill drawer today, but importing does not run until we ship it.