Give one product photo and get narrated videos, captions, social cards and web banners in three languages, with local prices




This workflow turns one product photo into a launch for three markets. You give it the photo, the product name and facts, and a language and a price for each market. It makes a narrated vertical video, a social card and a web banner in each language, with the local price.





You choose the languages, the prices, the backdrop and the setting. The photo and the facts stay the same for each market.
Every template in this workflow is yours to edit. Add your own logo, change the colors and fonts, move the layers or change the dimensions. Your next run uses the new design.
Run this workflow yourself in the app, or start it from your own code, your other apps or an AI assistant.
Install the workflow, fill in its inputs in your dashboard and run it. You can also share a form so that other people can run it.
Send the workflow uid and its inputs to one endpoint. The run continues in the background and returns the finished files.

Start a run when something happens in another app, such as a new row in a sheet or a new form entry.
Connect Claude or Cursor to the Bannerbear MCP server, and then ask it to run the workflow with your data.
This workflow is a starting point. Add, remove or reorder steps to make it do more. Each Bannerbear tool can be a step, with over 25 tools on offer.
The common questions about this workflow, and their answers
You type the name of each language, such as Spanish, French or German. The sample uses Latin-script languages only. The fonts in the templates are made for Latin letters, so test a language with another script before you use it.
AI writes the headline, call to action, caption and voiceover script. AI makes the three scenes, the voice and the music. The cut-out also uses AI. The templates, the captions and the prices are not AI. You type the prices, and the workflow does not translate them.
The prompts tell the AI to restate only the product name and the facts that you give, with no praise and no added claim. The AI can still make a mistake. The script has no numbers, so the voice does not say a price. The price shows on screen only. Check each text, or a back-translation of it, before you publish.
Each video is as long as its voiceover. The script has 28 words or fewer, so the video is short. The music is lower than the voice.
The example run on this page used 83 API credits and 21.1 AI credits. The cost of a run can change with your input, for example the length of a video or the number of rows in a spreadsheet. There is no charge for the workflow itself.
Yes. You do not have to open the app to run it. You can start it from your own code with the API, from a Zap in Zapier, or from an AI assistant that is connected to the Bannerbear MCP server. Each run takes your data and gives you the finished files.
Yes. The install gives you your own copy of the workflow and of its templates. You can change the templates, such as the colors, fonts and logo, and you can change the steps of the workflow.
A run is not instant, so the API answers at once, and the run continues in the background. Ask for the run to see its status. The status is queued, running, completed or failed. When the run is completed, it lists its outputs.
A sequence of steps that runs as one thing. Each step is an image render, an animation render, or a tool — and a step can use the output of an earlier step as its input.
Define its inputs, then supply them when you run it. Steps reference those inputs the same way they reference each other’s outputs.
POST to the workflow’s run endpoint with its inputs. The run is queued and reports progress as each step completes.
That is the point of inputs. Define the parts that change — a headline, an image URL, a name — and supply them per run.
Yes. Each run records every step, its inputs, its outputs and how long it took, so a failure points at the step that caused it rather than the whole workflow.
The run stops there and the failure is recorded against that step, with the outputs of the steps that already succeeded still available.
As long as its steps need — video work is not instant, and a workflow with several video steps takes minutes rather than seconds. Use the run’s progress or a webhook rather than holding a request open.
The workflow and its bundled templates are copied into your workspace, and the steps are rewritten to point at your copies rather than the originals.
Three on a trial. They are counted per workspace.
A workflow decides what gets made. An integration decides what triggers it and where the result goes. They are often used together.
Other ready-made workflows you can install







Cut out a product photo, place it in AI scenes, animate them and get narrated ads in three sizes






Give photos of empty rooms and get AI staged images, before and after videos, a social card and a seller brochure


Give one audio file and get AI-chosen waveform clips with illustrated art and captions, and show notes
Start a free trial with 30 API credits, no credit card required

