AI translation
StoreLingo uses DeepL for AI translation. DeepL is the highest-quality machine translator for European languages, especially for product copy.
How it works
When you click AI translate empty:
- We look up every empty field for the active locale.
- For each, we hash the source text and check our Translation Memory for a prior translation of the same string into the same locale. If found, we reuse it (no DeepL call, no charge against your AI char cap).
- On cache miss, we send the source to DeepL with your Glossary terms protected via XML placeholders, store the result in Translation Memory, and increment your usage.
Translation Memory
The cache is per-user, keyed by source locale + target locale + sha256 of normalized source text. A 100-product catalog translated into a second locale typically reuses 60-80% of strings from the first.
AI character cap
| Plan | Chars per month |
|---|---|
| Starter | 20,000 |
| Growth | 100,000 |
| Pro | 500,000 |
| Agency | 2,000,000 |
The cap resets at the start of each calendar month. Cached translations do not count.
Image alt text + custom fields
By default StoreLingo translates name, description, and summary on products and name, summary, description on CMS items. Use the Fields button in the action bar to add or remove translatable fields, including:
image-alt(or your alt-text field name) for SEO + accessibility on translated locales- Custom Webflow fields you want translated (
ingredients,specs,features, etc.)
The field name must match the Webflow field's API key. Adding a field backfills empty translation rows for every product + locale so you can start translating immediately.
Nested image fields (Webflow image objects like { url, alt }) are also handled. On sync we auto-detect these and create a virtual <fieldName>__alt translation row whose source is the original alt text. Add that virtual field name to translatable fields (e.g. add main-image__alt) and translate it like any other. On publish we reconstruct { url: <original>, alt: <translated> } and write it back to the same parent field.
Quality
DeepL is excellent for European languages and most common Asian ones. For very niche languages or domain-specific jargon (legal, medical), human review is recommended after AI translation. Use Approve in the editor to mark a field as human-reviewed.