01
Step 1
Gather the locked footage timeline with per-shot durations, the speaking pace the merchant specifies, and the list of claims the narration is permitted to make from the product records.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Write a product voiceover aligned with the footage
The edit is locked but the narration still runs long, so lines spill past the shots they describe. In this case, the immediate task is to write a product voiceover aligned with the footage. The workflow should produce a timed voiceover script whose lines land on the intended shots and stay inside the merchant's stated product facts.
Topic
Product Video Creation and Editing
Target keyword
product video voiceover generator
Copyable AI prompt
A prompt you can drop directly into Spark
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me write a product voiceover aligned with the footage.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the locked footage timeline with per-shot durations, the merchant's speaking pace, and the permitted claims list from product records]. Write each narration line to fit its shot's duration at the stated pace, landing the sentence boundary before the shot changes, and route any line that cannot fit without losing meaning back for a shot extension decision.
Return a timed voiceover script and check it against the footage plan and merchant records for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Write each narration line to fit its shot's duration at the stated pace, landing the sentence boundary before the shot changes, and route any line that cannot fit without losing meaning back for a shot extension decision.
03
Step 3
Deliver the timed voiceover script with line-level in and out points, then verify every line against the timeline and confirm each stated claim traces to a permitted record entry.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What happens when a line will not fit its shot?
The line is returned with the shortfall noted rather than compressed into vagueness, because trimming meaning to fit seconds silently weakens the claim; the decision to extend the shot or split the line belongs to the merchant.
Why write to the pace before recording?
The stated speaking pace converts each shot's duration into a word budget, so lines are born inside their window; rewriting after a recording overrun costs studio time and pushes later lines off their shots.
How are claims checked in the script?
Each factual statement is matched to an entry on the permitted claims list, and comparisons are allowed only against products named there; anything unmatched is flagged before the session, not retracted after.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.