Unequal Trial Counts Comparison Read

Create a 45-second creator voiceover from [two prompt variants with unequal trial counts] and [observed outcomes]. State both denominators before any success counts, explain why the totals alone do not rank the variants and ask for a balanced rerun with matched settings. Do not invent rates, significance or engagement. Provide exact spoken fractions and avoid naming a winner.

Use only the supplied facts and approved wording. If a necessary script or timing reference is missing, ask for it first. Produce the audio when supported; otherwise return the complete spoken script with pauses and a short production cue sheet, clearly labeled as a script. Use original voices and keep speech intelligible without music. Never claim an audio file exists unless it was generated.