MyMemory Translation Scraper

MyMemory Translation Scraper

Translate batches of text through the MyMemory API, up to a million segments per run. Each row returns the source text, the best machine translation, a match quality score, and the detected language. Export to CSV, JSON, Excel, or XML.

MyMemory is the world's largest translation memory, but calling its public API for bulk work means handling rate limits, email quotas, and pagination yourself. This Actor sends your list of texts to the MyMemory translation endpoint, respects the anonymous and authenticated quotas, and collects every result into one clean dataset. You pick the language pair from over 70 supported codes, and the Actor returns the translations with their match scores.

Who uses it	What they scrape MyMemory for
Localization engineers	Pre-translate UI strings or help articles before sending them to human review.
Content managers	Generate first-draft translations of product descriptions for multiple markets.
Data analysts	Build parallel corpora by translating survey responses or social media comments.
App developers	Populate a translation table for an app's interface strings across several languages.

What it does

This Actor sends an array of texts to the MyMemory translation API and returns each source string alongside its translated text, match quality, and detected language as a flat row.

• 🌐 70+ language pairs: source and target languages from Afrikaans to Yiddish, including regional variants like en-GB and pt-BR.
• 📊 Match quality score: each result includes a match percentage so you can filter for high-confidence translations.
• 📧 Quota uplift with email: pass an optional email address to raise the anonymous daily limit through MyMemory's public parameter.
• 📋 Batch input as a list: paste up to a million strings in the text array, or leave it empty to run a 10-phrase travel sampler.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

What you can do with MyMemory data

🌍 Pre-translate a content inventory.

A content team uploads 5,000 product titles in English and targets Spanish, French, and German, then exports the CSV to their TMS for post-editing.

📊 Build a bilingual glossary.

A linguist sends 2,000 domain-specific terms through the Actor and filters results with a match score above 80% to seed a termbase.

📱 Localize an app's string table.

A mobile developer pastes 500 UI strings, sets source to English and target to Japanese, and imports the JSON output directly into the project.

📝 Translate open-ended survey responses.

A researcher collects free-text answers in 10 languages, runs them through the Actor with auto-detected source, and analyzes the English translations.

Why choose this scraper

	What you get
No API wrapper to write	Call the MyMemory endpoint with a list of strings and get structured results back.
Quota handling built in	The Actor respects the public rate limits and uses your email to lift the anonymous cap.
Fixed output schema	Every row has the same columns: source text, translation, score, and detected language.

How it compares

No other Store actor targets MyMemory the same way, so the honest comparison is with the alternatives teams actually weigh.

	MyMemory Translation Scraper	Build it in-house	By hand
Setup	Run it now, zero config	Days of engineering	None, but hours per pull
When MyMemory changes	Maintained for you	You fix it	You re-learn the page
Proxies, retries, anti-bot	Built in	Your problem	Browser only
Output	Fixed JSON schema, CSV/Excel export	Whatever you build	Copy-paste
Cost	Pay per result	Engineering time	Analyst hours

Configure the run

Drive the Actor with a list of texts and a language pair. The source and target language dropdowns set the translation direction, and the optional email field raises your daily quota. The Input tab lists every parameter.

A first run with the defaults:

{
  "maxItems": 10,
  "texts": [
    "Hello, world!",
    "Good morning",
    "How are you?",
    "Thank you very much",
    "See you soon"
  ],
  "sourceLanguage": "en",
  "targetLanguage": "es"
}

A larger pull:

{
  "maxItems": 200,
  "texts": [
    "Hello, world!",
    "Good morning",
    "How are you?",
    "Thank you very much",
    "See you soon"
  ],
  "sourceLanguage": "en",
  "targetLanguage": "es"
}

Pricing

Pay-per-result: $0.01333 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$1.33
1,000 results	$13.33
10,000 results	$133.30

New Apify accounts start with $5 in free credit.

Free users

Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect up to 1,000,000 results per run.

Run it

1. Create a free Apify account with $5 in credit.
2. Open the MyMemory Translation Scraper.
3. Set your inputs and any filters, then click Start.
4. Export the results as CSV, Excel, JSON, or XML from the Dataset tab.

Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.

Use with AI agents (MCP)

Give an AI agent live access to MyMemory through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/mymemory-translation-scraper"

Then prompt it in plain language to run the scraper and read back the results.

Troubleshooting

Why am I getting no results?

Check that both the source and target language codes are set and that the texts array contains at least one non-empty string. If the array is empty, the sampler runs, but a run with an empty string may produce no output.

The run stopped early and I only got a few translations.

You likely hit the anonymous daily quota. Add a valid email address in the optional Email field and rerun. The MyMemory API raises the limit when an email is supplied.

Some translations look wrong or are in the wrong language.

Verify the source language code matches the actual language of your input texts. If you send Spanish text with source set to 'en', the translation quality will degrade.

I get an error about an invalid language code.

Use only the codes from the dropdown list. Free-form entries like 'esp' instead of 'es' will fail. Stick to the ISO codes provided in the input schema.

The match score is always 0 or very low.

A low match score means MyMemory found no close human translation for that segment. This is common for rare language pairs or very domain-specific text. The machine translation is still returned.

FAQ

Question	Answer
What is MyMemory?	MyMemory is a free translation memory built from the European Union's public documents and crowd-sourced corrections. It returns machine translations along with a match score that tells you how close the result is to a human-reviewed segment.
How many texts can I translate in one run?	You can set the maximum up to 1,000,000 items. The actual throughput depends on the MyMemory API rate limits and whether you supply an email to raise the anonymous quota.
Do I need a MyMemory API key?	No. The public endpoint works without authentication. Adding an email address in the optional field raises the daily quota, but no key or registration is required.
Which languages are supported?	Over 70 languages, from Afrikaans to Yiddish. The dropdowns include regional codes like en-GB, pt-BR, and zh-CN so you can target specific locales.
What does the match score mean?	It is a percentage that indicates how closely the returned translation matches an existing human translation in the MyMemory database. Higher scores usually mean more reliable output.
Can I leave the text list empty?	Yes. When the texts array is empty, the Actor runs a built-in sampler of 10 common travel phrases so you can test the output format before committing a large batch.
How do I export the translations?	The dataset is stored in Apify's key-value store and can be downloaded as CSV, JSON, Excel, or XML from the run console or via the API.
Does the Actor auto-detect the source language?	You must pick a source language from the dropdown. The MyMemory API can detect language in some cases, but this Actor sends the code you select to ensure consistent results.
Is there a cost to use MyMemory?	The MyMemory API is free for anonymous use up to a daily quota. Supplying an email raises that limit. The Actor itself consumes Apify platform credits based on run time.
Can I translate into multiple target languages at once?	One run translates from one source language to one target language. To get multiple targets, run the Actor once per language pair with the same input texts.

Related actors

• website-content-crawler: Use this to extract raw text from web pages that you can then feed into the MyMemory Translation Scraper as input texts.
• youtube-transcript-scraper: Use this to pull video transcripts in one language, then pipe the text into the MyMemory Translation Scraper for translation.

Browse the full ParseForge collection for more scrapers.

🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by Translated srl. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.