Translation Memory: how it works
Prefer to watch? This clip starts at the part about translation memory, which is for sentences, and shows how it keeps repeated wording consistent.

A Translation Memory (TM) is a database of every sentence-level translation your team has ever produced. Every time Taia's AI or a human linguist translates a segment, that segment pair (source + target) is saved. The next time a similar sentence appears, Taia retrieves the stored translation and suggests it automatically.
The core idea
Imagine you've translated your software UI into French. Six months later, you update the product and need to translate it again. Around 70% of the sentences are identical or nearly identical to last time. Without a TM, those sentences get translated from scratch again. With a TM, they come back from your memory, so the wording stays consistent and your reviewers have far less to fix.
What that does to the price depends on the kind of translation. On AI translation you pay credits per word either way. On Professional translation matches are billed at a lower per-word rate, so a TM saves money there. The two are separated below.
Match scores
Not every stored segment is a perfect match. Taia assigns a match score (0–100%) based on how similar the stored source text is to the current segment:
- 100% — Identical. The stored translation can be applied as-is, automatically if you switch on Auto-apply TM matches when you start an AI translation.
- 95–99% — Near-exact (punctuation or casing differs). Apply with a quick review.
- 75–94% — Fuzzy match. The words are similar but not identical. Use as a starting point.
- Below 75% — Too different; not suggested.
For Professional translation orders, higher match scores mean a lower per-word rate. See Understand match scores.
How TM fills up
A TM grows from two sources:
- Active translation — every segment a linguist confirms in the CAT editor is saved into the TM automatically.
- TMX import — you can upload existing translation memories from other tools in TMX format. See Import a TMX file.
TM and AI translation
A TM shapes AI translation in three ways:
- Exact matches, when you switch it on. In the AI translation dialog, Auto-apply TM matches places your 100% matches into the draft before the AI runs, so fully matched segments don't need the AI. Switch it off and Taia doesn't pre-fill them; the two paths below still apply.
- Examples for the AI. On Advanced and Premium, similar sentences (75% and above) from your memory are handed to the AI as examples to follow, whether or not that switch is on. On Standard, your memories are shared with the translation engine, which uses them on its own side.
- Matches in the editor. Matches of 75% and above show in the Translation Memory panel of the CAT editor (95% and up are marked as high quality), where you can insert them yourself. See Use TM matches in the CAT editor.
This is how your TM guides the AI to sound like your brand over time: the more your team has translated in a particular style, the more the AI draws on that context for future projects.
What it costs
AI translation credits don't change with a TM. Credits are charged per word whether a segment comes from the AI or from your memory, so a TM doesn't make AI translation cheaper. What it gives you is consistency, and less to correct at review.
Professional translation is different. There, TM matches and repetitions are billed at a discounted per-word rate: the higher the match score, the lower the rate. See Understand match scores.
Languages and regional variants
Taia never takes a translation from a different variant of your project's language. That holds for matches applied to your files, the match analysis on a quote, the suggestions in the CAT editor, and the examples the AI translation draws on. Each regional or script variant counts as a language of its own:
- A
de-AT(Austrian German) translation is never used for ade-DE(German, Germany) project, and the other way round. - A TM entry stored with a plain code such as
deorES(common in TMX files from other tools) doesn't say which variant it is. Taia can still show it as a suggestion in the CAT editor and give it to the AI as an example, ranked below an entry in your exact variant that matches just as well. It's never applied to your file automatically, and it never counts towards the match analysis on a quote. For languages where the variant is the script, such as Serbian and Chinese, a plain code is never used, because it doesn't say which alphabet the text is in. sr-Latn(Serbian, Latin script) andsr-Cyrl(Serbian, Cyrillic script) never match each other. The same goes forzh-CN(Simplified Chinese) andzh-TW(Traditional Chinese).
Upper or lower case in a language code makes no difference. A TMX file from another tool that labels its German DE-DE matches a de-DE project exactly.
So if your existing memory is British English and your new project is American English, the memory won't supply matches for it. To reuse it, create the project in the same variant as the memory.
Multiple TMs
You can create multiple TMs — one per language pair, one per product, one per department — and attach multiple TMs to a single project. Taia queries all of them and uses the highest-scoring match.
A TM can be thrown away
A memory that has learned the wrong things is not a permanent problem. Any TM can be deleted and replaced with an empty one at any time, and doing so leaves your projects and delivered translations untouched.
This matters most while you are evaluating Taia. Every edit a reviewer makes goes into the memory, test edits included, so a memory built during a trial is a mix of real terminology and experimentation. Practice freely, then delete the TM and create a clean one before real work starts. See start a TM over.