One campaign. Every market.
Localizing shouldn't mean rebuilding. Change the market input and rerun — copy retranslated in your tone, voiceover re-voiced, visuals recomposed. The campaign stays one campaign.
Localized, not just translated
Text nodes carry your brand voice into each language, so the Berlin ad sounds like you in German — not like a phrasebook.
brand tone held across languagesPer-market is a rerun
The pipeline is the campaign. Each market is one input change; only the language-dependent steps recompute.
one input change per marketOne subscription, all of it
Translation, voice and image models in one place — localization stops being four vendors and a spreadsheet.
translate · voice · image — one billBuilt once. Run forever.
Build the master campaign once.
Script, scenes, voiceover, sizes — the full pipeline, wired to your brand kit, approved once.
Switch the market, keep the craft.
A language input feeds the translate and voice nodes. The visual composition, pacing and brand treatment stay exactly as approved.
Review per node — a native speaker checks the copy node, not a finished video that's expensive to redo.
Every market lands as a set.
Outputs arrive named and sized per market and channel — ready for the local team or the ad platform.
Ship it as an app so regional teammates run their own market without touching the canvas.
The next market is one input.
Build the master once on the free tier, then watch a market swap rerun only the language-dependent steps — with the cost on screen before you press run.
How this works in practice.
How is this different from machine translation?
Translation is one node of it. The pipeline also re-voices the audio in the new language, recomposes visuals that carry text, and keeps your brand tone in the copy — so the output is a localized ad, not a subtitled one.
Can native speakers review before anything renders?
Yes. Every node's output is reviewable on the canvas, so a native speaker approves the translated copy node before the expensive voice and video steps run.
What parts of the campaign get localized?
Copy and captions, the voiceover, visuals that need recomposing for the market, and the export sizes per channel. The approved composition, pacing and brand treatment stay fixed.
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.
Say it everywhere.
Start free: build the master once, then watch a market swap rerun the whole campaign.