The ad runs while you work.
Lead-gen video ads for clinics, contractors, salons and firms: a script in your voice, an AI voiceover, spokesperson-style delivery, captions and channel sizes. One pipeline per offer — rerun it for every city and season, no shoot to schedule.
Scripted in your voice
Paste your website URL and the brand kit is built for you: colors, fonts, voice, logo. Every script sounds like your front desk on a good day, not a generic ad read.
your-brand.kit → every script nodeA spokesperson with no shoot
A lipsync node turns a still image and the voiceover into spokesperson-style delivery — always presented as AI-generated, never as a real endorser — with nothing to schedule and nobody to book.
still + voice → talking spotRerun per city and season
One pipeline per offer. Swap the city or the seasonal hook and rerun; only the changed steps recompute, so the fall version is a rerun, not a production cycle.
changed steps recompute · rest is cachedBuilt once. Run forever.
The offer goes in, a script comes out.
Type the offer — a spring tune-up, a new-patient special, a free consultation — and a text node drafts the script against your brand kit's tone.
Edit it on the canvas; the downstream nodes pick up the change automatically.
Give the script a voice, then a face.
A voice node reads the script; a lipsync node animates a still into spokesperson-style delivery, synced to the audio. The result is labeled as AI-generated, and a human-review pause lets you approve every take before it ships.
Captions land on top for sound-off feeds, and a sizing step cuts the spot for every channel.
One pipeline per offer, forever.
When the season turns or a new location opens, change the offer text and rerun. Only the steps after the change recompute.
Publish it as an app for the office: whoever owns marketing this month types the offer, presses run, and stays on-brand without opening the canvas.
One offer in, one spot out.
Open the services-ad template, paste your URL for the brand kit, and run it on the free tier. The credit cost shows on the canvas before you press run.
How this works in practice.
What is an AI spokesperson video?
A video ad where a lipsync model animates a still image to deliver a voiceover, so the spot has spokesperson-style, direct-to-camera delivery without a filmed presenter. In Orisu, a voice model reads your script and the lipsync node syncs the delivery to it — the result is presented as AI-generated, not as a real person's endorsement.
Is the spokesperson a real person?
No, and Orisu never presents it as one. The delivery is AI-generated from a still image and an AI voiceover, reading a script you approved against your brand kit. A human-review pause holds every spot for your sign-off before it ships, and it should always run labeled as AI-generated rather than as a real endorser.
Can I run the same ad in different cities or seasons?
Yes. The offer is just a text input. Change the city or the seasonal hook and rerun; only the steps after the change recompute, so a localized or seasonal version costs a rerun, not a rebuild.
Do I have to build this pipeline myself?
No. Start from a template, or describe what you want and Orisu drafts the pipeline: nodes, wires and all. You can also build it step by step if you prefer.
What does it cost to run?
Every node shows its estimated credit cost on the canvas, and a run shows its total before you press it. The free tier needs no credit card.
Can my team use it without learning the canvas?
Yes. App Mode turns the pipeline into a simple form: inputs on top, a run button, outputs below. No canvas knowledge needed.
Can I change models later?
Yes. Models sit behind the same ports, so you can swap one without rewiring the workflow.
Put a spokesperson on it.
Start free: paste your URL for the brand kit, pick a template, and have a lead-gen ad pipeline running today.