{"slug": "google-translate", "name": "Google Translate", "category": "other", "category_name": "Other software", "description": "", "recommenders": 4, "commenters": 16, "warners": 3, "score": 3.117, "rising": -1.31, "first": "2026-03-18", "latest": "2026-10-02", "why": "I use Google Translate quite a lot and it's pretty good even for obscure languages.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 9, "compare": 1, "warn": 3}, "spark": [0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use Google Translate quite a lot and it's pretty good even for obscure languages.", "icon": true, "domain": null, "github_repo": null, "official_url": "https://translate.google.com", "pricing": "", "aliases": ["Google Translate"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 783849552, "item_id": 48990597, "url": "https://news.ycombinator.com/item?id=48990597", "by": "jdw64", "date": "2026-07-21", "stance": "recommend", "quote": "So I use Google Translate when I need to translate sentences I don't know.", "excerpt": "Actually, if you use an LLM translator to post on Hacker News, it gets flagged immediately. HN doesn't even allow LLMs as translators. So I use Google Translate when I need to translate sentences I don't know. (I think HN itself probably uses something like fangram on the database side to check AI similarity for new comments.) Even translation gets flagged immediately if it's done with an LLM, so I think actual LLM-g", "context": "", "use_case": "translating sentences", "switched_from": "DeepL", "story": "Ask HN: If you're running LLM bots on HN, can you at least report results?"}, {"id": 776247616, "item_id": 48515476, "url": "https://news.ycombinator.com/item?id=48515476", "by": "tim333", "date": "2026-06-13", "stance": "recommend", "quote": "I use Google Translate quite a lot and it's pretty good even for obscure languages.", "excerpt": "I use Google Translate quite a lot and it's pretty good even for obscure languages. The voice to text thing on youtube videos has improved a lot in the last five years.", "context": "", "use_case": "translation", "switched_from": "", "story": "\"Don't You Just Upload It to ChatGPT?\""}, {"id": 768499281, "item_id": 48031205, "url": "https://news.ycombinator.com/item?id=48031205", "by": "fiedzia", "date": "2026-05-05", "stance": "recommend", "quote": "we have some that have very high bar of engineering (firefox, google translate)", "excerpt": "> Ever seen most high profile apps in the last 10-15 years? No, but the ones I am paying for are few and with rather solid development record. Looking at top android apps, we have some that have very high bar of engineering (firefox, google translate), some just useful dataset (cooking recipes), but again, even the simple ones outcompeted tons of alternatives. > most enterprise software I am not saying enterprise sof", "context": "", "use_case": "translation", "switched_from": "", "story": "Ask HN: The death of software development as a job?"}, {"id": 759810576, "item_id": 47488161, "url": "https://news.ycombinator.com/item?id=47488161", "by": "gus_massa", "date": "2026-03-23", "stance": "recommend", "quote": "my recommendation is to use Google Translate (or something similar) that does a good but quite literal translation.", "excerpt": "She wanted to do the courses/tracks sequentially to complete them and get the certificate (IIRC you have to pay to get the certificate). Now she is using Kotlin to make apps for the tablet of our kids, but she didn't take any course of Kotlin. --- Are you using AI to write the comments? The guidelines ask not to use it. https://news.ycombinator.com/newsguidelines.html > Don't post generated comments or AI-edited comm", "context": "", "use_case": "translating comments", "switched_from": "", "story": "Ask HN:35,0 CS background, built real apps with AI, need suggestion"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 797996064, "item_id": 49874754, "url": "https://news.ycombinator.com/item?id=49874754", "by": "internet_points", "date": "2026-09-28", "stance": "warn", "quote": "these days it \"interprets\" way too much, confabulating like an LLM", "excerpt": "I miss the old Google Translate. I use it for learning languages (translating little snippets, lyrics etc.) and these days it \"interprets\" way too much, confabulating like an LLM and inserting stuff that's way beyond what's in the text. I have to remove words and rewrite and look for other sources to be sure it's actually translating what I'm inputting and not something it just made up to make it sound good.", "context": "", "use_case": "learning languages, translating snippets", "switched_from": "", "story": "When did Google get so weird?"}, {"id": 792746496, "item_id": 49546656, "url": "https://news.ycombinator.com/item?id=49546656", "by": "itake", "date": "2026-09-03", "stance": "warn", "quote": "how Google translate assumes \"Anh\" means \"brother\"", "excerpt": "I love/hate how Google translate assumes \"Anh\" means \"brother\" or \"em\" means \"girl\". This confusion has resulted in Vietnamese people unintentionally describing incest or gay relationships. [0] - What she actually meant was \"brother\" in the sense that he is a family friend and neighbor.", "context": "", "use_case": "Vietnamese translation", "switched_from": "", "story": "The shrinking landscape of linguistic diversity in the age of LLMs"}, {"id": 789134160, "item_id": 49320885, "url": "https://news.ycombinator.com/item?id=49320885", "by": "adrian_b", "date": "2026-08-16", "stance": "warn", "quote": "there never was even a single sentence that I could let exactly as generated by \"Google translate\".", "excerpt": "LLMs were not available in 2021, but \"Google translate\" is much older. Such translations were not unusual. Around 2017 to 2019 I used a lot \"Google translate\", because it saved time despite its flaws, but there never was even a single sentence that I could let exactly as generated by \"Google translate\". In each sentence I had to change at least a word or two, and many were hilarious. This was for translations between", "context": "", "use_case": "English-German translation", "switched_from": "", "story": "Research papers using \"kidney disappointment\" instead of \"kidney failure\""}]}], "who": [{"by": "NarcisMirandes", "context": "lives in a small European country, uses translations daily", "url": "https://news.ycombinator.com/item?id=49183735", "date": "2026-08-05"}, {"by": "jdw64", "context": "writes in Korean", "url": "https://news.ycombinator.com/item?id=48758215", "date": "2026-07-02"}, {"by": "GreenSalem", "context": "professional translator (quoted)", "url": "https://news.ycombinator.com/item?id=48513641", "date": "2026-06-12"}, {"by": "tkgally", "context": "Japanese-English translator and lexicographer", "url": "https://news.ycombinator.com/item?id=48420657", "date": "2026-06-05"}], "tags": [], "use_cases": ["translation", "machine translation", "web scraping proxy", "learning languages, translating snippets", "vietnamese translation", "english-german translation"], "compared": [{"slug": "deepl", "name": "DeepL", "co": 3, "switched_from": 1, "switched_to": 1}, {"slug": "kagi-translate", "name": "Kagi Translate", "co": 3, "switched_from": 0, "switched_to": 1}, {"slug": "chatgpt", "name": "ChatGPT", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "gemini", "name": "Gemini", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "kagi", "name": "Kagi", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48507278", "title": "\"Don't You Just Upload It to ChatGPT?\"", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49929970", "title": "Meta's Muse is fantastic for web scraping", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49870367", "title": "When did Google get so weird?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49497996", "title": "The shrinking landscape of linguistic diversity in the age of LLMs", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49319389", "title": "Research papers using \"kidney disappointment\" instead of \"kidney failure\"", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49233423", "title": "Ask HN: What are you working on? (August 2026)", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"compare": 1, "recommend": 1}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 1}, "2026-06": {"neutral": 4, "recommend": 1}, "2026-07": {"neutral": 1}, "2026-08": {"neutral": 2, "warn": 1}, "2026-09": {"warn": 2}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 798887361, "item_id": 49930460, "url": "https://news.ycombinator.com/item?id=49930460", "by": "wraptile", "date": "2026-10-02", "stance": "neutral", "quote": "Back in the 2010s I used Google Translate for years to scrape hard targets like LinkedIn", "excerpt": "Every time a new tool launches there's a good window where it can act as a scraping proxy. Back in the 2010s I used Google Translate for years to scrape hard targets like LinkedIn but these windows are much shorter these days as scraping is so much bigger. One thing with Muse though is that you can scrape Meta's own sites which are currently all going under login walls and restricting discovery/search entirely.", "context": "", "use_case": "web scraping proxy", "switched_from": "", "story": "Meta's Muse is fantastic for web scraping"}, {"id": 797996064, "item_id": 49874754, "url": "https://news.ycombinator.com/item?id=49874754", "by": "internet_points", "date": "2026-09-28", "stance": "warn", "quote": "these days it \"interprets\" way too much, confabulating like an LLM", "excerpt": "I miss the old Google Translate. I use it for learning languages (translating little snippets, lyrics etc.) and these days it \"interprets\" way too much, confabulating like an LLM and inserting stuff that's way beyond what's in the text. I have to remove words and rewrite and look for other sources to be sure it's actually translating what I'm inputting and not something it just made up to make it sound good.", "context": "", "use_case": "learning languages, translating snippets", "switched_from": "", "story": "When did Google get so weird?"}, {"id": 792746496, "item_id": 49546656, "url": "https://news.ycombinator.com/item?id=49546656", "by": "itake", "date": "2026-09-03", "stance": "warn", "quote": "how Google translate assumes \"Anh\" means \"brother\"", "excerpt": "I love/hate how Google translate assumes \"Anh\" means \"brother\" or \"em\" means \"girl\". This confusion has resulted in Vietnamese people unintentionally describing incest or gay relationships. [0] - What she actually meant was \"brother\" in the sense that he is a family friend and neighbor.", "context": "", "use_case": "Vietnamese translation", "switched_from": "", "story": "The shrinking landscape of linguistic diversity in the age of LLMs"}, {"id": 789134160, "item_id": 49320885, "url": "https://news.ycombinator.com/item?id=49320885", "by": "adrian_b", "date": "2026-08-16", "stance": "warn", "quote": "there never was even a single sentence that I could let exactly as generated by \"Google translate\".", "excerpt": "LLMs were not available in 2021, but \"Google translate\" is much older. Such translations were not unusual. Around 2017 to 2019 I used a lot \"Google translate\", because it saved time despite its flaws, but there never was even a single sentence that I could let exactly as generated by \"Google translate\". In each sentence I had to change at least a word or two, and many were hilarious. This was for translations between", "context": "", "use_case": "English-German translation", "switched_from": "", "story": "Research papers using \"kidney disappointment\" instead of \"kidney failure\""}, {"id": 787759475, "item_id": 49234967, "url": "https://news.ycombinator.com/item?id=49234967", "by": "muazzam", "date": "2026-08-09", "stance": "neutral", "quote": "found myself jumping between ChatGPT and Google Translate", "excerpt": "I've been working on a Persian classical poetry archive with LLM-generated translation. As a poetry enthusiast but a non-speaker of Persian, I wanted to read Rumi, Hafiz, and Bedil, but found myself jumping between ChatGPT and Google Translate. I sourced my data from Ganjoor, which was luckily available via their public API. Then I quickly put together a website with bring-your-own-key translation feature. For now, t", "context": "", "use_case": "translating poetry", "switched_from": "", "story": "Ask HN: What are you working on? (August 2026)"}, {"id": 786939761, "item_id": 49183735, "url": "https://news.ycombinator.com/item?id=49183735", "by": "NarcisMirandes", "date": "2026-08-05", "stance": "neutral", "quote": "translation. https://translate.google.com/", "excerpt": "I have tried and it works well. I bookmark it to use it in next days. What I do now: I am in a small country in Europe and I use translations a lot, every day literally. I am in a Mac and I have a \"space\" dedicated to that with three things: - dictionary and Tesaurus. Free app in all Macs - translation. https://translate.google.com/ - a Excel file where I save and review the new words My first impressions: - Your too", "context": "lives in a small European country, uses translations daily", "use_case": "translation", "switched_from": "", "story": "Show HN: Vocab Top \u2013 AI-powered vocabulary builder that helps you retain words"}, {"id": 783849552, "item_id": 48990597, "url": "https://news.ycombinator.com/item?id=48990597", "by": "jdw64", "date": "2026-07-21", "stance": "recommend", "quote": "So I use Google Translate when I need to translate sentences I don't know.", "excerpt": "Actually, if you use an LLM translator to post on Hacker News, it gets flagged immediately. HN doesn't even allow LLMs as translators. So I use Google Translate when I need to translate sentences I don't know. (I think HN itself probably uses something like fangram on the database side to check AI similarity for new comments.) Even translation gets flagged immediately if it's done with an LLM, so I think actual LLM-g", "context": "", "use_case": "translating sentences", "switched_from": "DeepL", "story": "Ask HN: If you're running LLM bots on HN, can you at least report results?"}, {"id": 780131440, "item_id": 48758215, "url": "https://news.ycombinator.com/item?id=48758215", "by": "jdw64", "date": "2026-07-02", "stance": "neutral", "quote": "I'm actually using Google Translate and Papago (a Korean translator) to translate them.", "excerpt": "I'm sorry, but I didn't use AI. The thing that's really hard about this is that the language I write in is Korean, and in the process of translating my words, the sentences and context I can use are limited. Most of the time, I use officially translated versions of Confucian classics, but I'm actually using Google Translate and Papago (a Korean translator) to translate them. The words I use are fixed, and since the r", "context": "writes in Korean", "use_case": "translating Korean writing", "switched_from": "", "story": "Why I Stopped Arguing with People"}, {"id": 779096528, "item_id": 48693533, "url": "https://news.ycombinator.com/item?id=48693533", "by": "miiiiiike", "date": "2026-06-26", "stance": "neutral", "quote": "using Google Translate for almost two decades now", "excerpt": "What a bad idea AI therapy is and I don\u2019t know too many people who are using AI art commercially. Translators, sure. But we\u2019ve been using Google Translate for almost two decades now. You didn\u2019t need AI for your plumbing. My dad had a whole set of books on household chores that we used to fix everything. I do more of the work around my house than most. I won\u2019t touch tall trees to fuck with my breaker box. I do most of", "context": "", "use_case": "translation", "switched_from": "", "story": "'Cost Me the Election': Data Centers Trigger Voter Backlash"}, {"id": 776247616, "item_id": 48515476, "url": "https://news.ycombinator.com/item?id=48515476", "by": "tim333", "date": "2026-06-13", "stance": "recommend", "quote": "I use Google Translate quite a lot and it's pretty good even for obscure languages.", "excerpt": "I use Google Translate quite a lot and it's pretty good even for obscure languages. The voice to text thing on youtube videos has improved a lot in the last five years.", "context": "", "use_case": "translation", "switched_from": "", "story": "\"Don't You Just Upload It to ChatGPT?\""}, {"id": 776218257, "item_id": 48513641, "url": "https://news.ycombinator.com/item?id=48513641", "by": "GreenSalem", "date": "2026-06-12", "stance": "neutral", "quote": "we used to paste uncooperative sentences into Google Translate", "excerpt": "Despite the protests, he admits using AI and then charging his clients full price... \"But maybe I will ask Claude\u2019s opinion, and if one of the suggestions is smart\u2014cutting a paragraph, for instance, or clarifying a sentence\u2014I might accept it. When I started translating 15 years ago, we used to paste uncooperative sentences into Google Translate to see if it had interesting ways to phrase things differently. Then came", "context": "professional translator (quoted)", "use_case": "alternative phrasing in translation", "switched_from": "", "story": "\"Don't You Just Upload It to ChatGPT?\""}, {"id": 774730513, "item_id": 48420657, "url": "https://news.ycombinator.com/item?id=48420657", "by": "tkgally", "date": "2026-06-05", "stance": "neutral", "quote": "The neural Google Translate, while still far from perfect, was suddenly useful for some purposes.", "excerpt": "My first came in late 2016, when Google Translate switched from statistical machine translation to a neural-network-based system. I had worked as a Japanese-English translator and lexicographer for two decades, and I had been testing various machine-translation services over the years. For translation between Japanese and English, at least, they were uniformly terrible: the output for genuine texts was mostly incompr", "context": "Japanese-English translator and lexicographer", "use_case": "machine translation", "switched_from": "", "story": "What was your \"Oh Shit\" moment with GenAI?"}, {"id": 774564960, "item_id": 48410310, "url": "https://news.ycombinator.com/item?id=48410310", "by": "pramodbiligiri", "date": "2026-06-05", "stance": "neutral", "quote": "using Google Translate", "excerpt": "A repo with the English translation of each of the rules files, using Google Translate: https://github.com/pramodbiligiri/open-code-review-rules. The original rules files (in Chinese): https://github.com/alibaba/open-code-review/tree/main/internal/config/rules/rule_docs", "context": "", "use_case": "translating rules files", "switched_from": "", "story": "Alibaba/Open-Code-Review"}, {"id": 768499281, "item_id": 48031205, "url": "https://news.ycombinator.com/item?id=48031205", "by": "fiedzia", "date": "2026-05-05", "stance": "recommend", "quote": "we have some that have very high bar of engineering (firefox, google translate)", "excerpt": "> Ever seen most high profile apps in the last 10-15 years? No, but the ones I am paying for are few and with rather solid development record. Looking at top android apps, we have some that have very high bar of engineering (firefox, google translate), some just useful dataset (cooking recipes), but again, even the simple ones outcompeted tons of alternatives. > most enterprise software I am not saying enterprise sof", "context": "", "use_case": "translation", "switched_from": "", "story": "Ask HN: The death of software development as a job?"}, {"id": 764262784, "item_id": 47766424, "url": "https://news.ycombinator.com/item?id=47766424", "by": "ben_w", "date": "2026-04-14", "stance": "neutral", "quote": "I use Google Translate (literally the same architecture, last I heard), and when it works, great.", "excerpt": "> Particularly machine translations are no worse than what an untrained native speaker would come up with, and much better than traditional translators Sometimes. I use Google Translate (literally the same architecture, last I heard), and when it works, great. Every single time I've tried demonstrating that it can't do Chinese by quoting the output it gives me from English-to-Chinese, someone replies to tell me that ", "context": "", "use_case": "machine translation", "switched_from": "", "story": "Stanford report highlights growing disconnect between AI insiders and everyone"}, {"id": 759810576, "item_id": 47488161, "url": "https://news.ycombinator.com/item?id=47488161", "by": "gus_massa", "date": "2026-03-23", "stance": "recommend", "quote": "my recommendation is to use Google Translate (or something similar) that does a good but quite literal translation.", "excerpt": "She wanted to do the courses/tracks sequentially to complete them and get the certificate (IIRC you have to pay to get the certificate). Now she is using Kotlin to make apps for the tablet of our kids, but she didn't take any course of Kotlin. --- Are you using AI to write the comments? The guidelines ask not to use it. https://news.ycombinator.com/newsguidelines.html > Don't post generated comments or AI-edited comm", "context": "", "use_case": "translating comments", "switched_from": "", "story": "Ask HN:35,0 CS background, built real apps with AI, need suggestion"}, {"id": 758795731, "item_id": 47424733, "url": "https://news.ycombinator.com/item?id=47424733", "by": "keysersoze33", "date": "2026-03-18", "stance": "compare", "quote": "better for me than Google Translate", "excerpt": "I've been a Kagi Pro user for several years now, and to be honest, the models from the pro tier aren't that useful compared to the free versions of Gemini & ChatGPT. For me, I pay for Kagi pro for search without Google/Bing enshittification, their Translate (which I use quite often while I'm learning German/working in German - better for me than Google Translate), and their Summarizer. I pay for Claude, and also occa", "context": "", "use_case": "translation", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}]}