The Scenario
You are a localization engineer. The Spanish translation memory in Crowdin has accumulated over three years of work and before migrating to a new TMS, you need to export every source and target pair into an Excel workbook for quality review.
The goal: find duplicates, flag inconsistencies, remove segments translated incorrectly. Your QA lead will work through the workbook row by row, adding notes in column D.
The slow version:
- Export the TM from Crowdin as a TMX file
- Import the TMX into a converter to get a CSV
- Import the CSV into Excel
- Realize the TMX export included metadata columns your QA lead does not need
- Spend an hour cleaning up columns and removing noise
- The QA lead gets the workbook four days after you planned to hand it off.
The fast version is one prompt.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent inside your Excel workbook that pulls the TM segments directly from Crowdin and writes them in a clean format, so you skip the TMX → CSV → cleanup pipeline entirely.
Open the SheetXAI sidebar and type:
Export the Crowdin translation memory ID from cell A1 as a structured list. Write all English source text and Spanish target translation pairs into the TM Review tab starting at row 2. Add a column C with the creation date for each segment.
SheetXAI calls the Crowdin API, retrieves the TM segments, and writes source, target, and creation date into the workbook. Your QA lead starts reviewing immediately.
What You Get
A TM export on the TM Review tab with one row per segment pair:
- Column A — English source text
- Column B — Spanish target translation
- Column C — creation date of the segment
The creation date column is what QA needs most. Segments from three years ago may predate your current style guide. Sorting by creation date descending lets the QA lead prioritize recent high-volume segments and flag old ones for a second pass.
What If the Data Is Not Quite Ready
TM exports for migration purposes need more than a raw dump of segments.
When the export should exclude low-confidence segments
Export all TM segments from TM ID in cell A1 of the TM Review tab where the confidence score is 80 or higher. Write source, target, and confidence score into columns A through C. Label the column header row.
When the QA lead wants duplicate source strings flagged
Export all TM segments from TM ID in cell A1. Write source and target into columns A and B of the TM Review tab. In column C, write "DUPLICATE" if the same source string appears more than once in the export, and "UNIQUE" if it appears once. Sort duplicates to the top.
When you need to import corrected segments back into Crowdin
After the QA pass, you have reviewed segments on the Clean tab ready to push back.
Create new TM segments in Crowdin TM ID from cell A1 of the TM Review tab for each row in the Clean tab where column A is the English source text and column B is the corrected Spanish translation. Write "IMPORTED" into column C for each success.
When you need to export, deduplicate, and import the cleaned version back in one operation
Export all TM segments from TM ID in cell A1 of the TM Review tab into a temporary tab. Identify duplicate source strings and keep only the most recently created translation for each. Write the deduplicated list to the Clean tab. Then create new TM segments in a new Crowdin TM named "Spanish Clean v2" using column A as source and column B as target from the Clean tab.
The pattern: export for review, clean in the workbook, push back the corrected version. The workbook is the workspace for the migration.
Try It
Get the 7-day free trial of SheetXAI and open a workbook with your Crowdin TM ID in cell A1, then ask it to export the source and target pairs. The Crowdin integration is included in every SheetXAI plan. For related workflows, see how to import glossary terms into Crowdin or the Crowdin in Excel overview.