--- title: ML Kit expands into NLP with Language Identification and... description: Firebase's ML Kit adds two new on-device NLP APIs: Language Identification and Smart Reply. Language Identification recognizes 110 languages, typically needs... canonical: https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: ML Kit expands into NLP with Language Identification and Smart Reply | daily.dev og:description: Firebase's ML Kit adds two new on-device NLP APIs: Language Identification and Smart Reply. Language Identification recognizes 110 languages, typically needs... og:url: https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds og:image: https://api.daily.dev/og/posts/aHXbo6WdS.png og:image:alt: ML Kit expands into NLP with Language Identification and Smart Reply og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # ML Kit expands into NLP with Language Identification and Smart Reply **[Firebase](https://daily.dev/sources/firebase-blog)** · 5 min read · 0 upvotes · 0 comments ## Summary Firebase's ML Kit adds two new on-device NLP APIs: Language Identification and Smart Reply. Language Identification recognizes 110 languages, typically needs only a few words, and responds within 1-2ms on iOS and Android. Smart Reply generates chat reply suggestions based on up to the last 10 messages, running fully on-device with no server calls, and launches with English support. Both use TensorFlow Lite models built on SentencePiece text encoding and Transformer architecture, and are available via simple Kotlin/Swift function calls on iOS 9.0+ and Android 4.1+. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How fast is ML Kit's Language Identification API and how many languages does it support? ML Kit's Language Identification API recognizes 110 different languages and typically only needs a few words of text to make an accurate determination. It responds within 1 to 2 milliseconds across both iOS and Android phones, running fully on-device. If no language can be confidently identified, it returns a BCP-47 code of 'und' for undetermined. _Developers picking on-device NLP tools can track new ML Kit API releases like this on daily.dev._ ### How does the Smart Reply API in ML Kit generate chat reply suggestions? Smart Reply uses a machine-learned model executed with TensorFlow Lite, built on SentencePiece text encoding and Transformer architecture, running entirely on-device without sending message history to a server. It generates suggestions based on the last 10 messages in a conversation, works with as few as one prior message, and includes a sensitive-topic detector to avoid replying to profanity or personal hardship. It launches with English support only. _Teams weighing on-device versus cloud NLP for chat features can follow API updates like this on daily.dev._ ### What platforms and OS versions support Firebase ML Kit's Smart Reply and Language Identification APIs? Both APIs run fully on-device and are available on iOS 9.0 and higher and Android 4.1 and higher, as part of the latest ML Kit SDK. They are called with simple function calls, such as suggestReplies() for Smart Reply and identifyLanguage() for Language Identification, both using Kotlin in the documented examples. _Mobile developers integrating on-device ML SDKs can keep up with platform requirements like these on daily.dev._ ## Similar posts on daily.dev - [Android AI Just Changed — and Most Developers Haven’t Noticed Yet](https://daily.dev/posts/android-ai-just-changed-and-most-developers-haven-t-noticed-yet-ew4d0vzac) · ProAndroidDev · 0 upvotes · 0 comments - [Build intelligent Android apps: On-device inference](https://daily.dev/posts/build-intelligent-android-apps-on-device-inference-kynhfi0rx) · Android Developers Blog · 0 upvotes · 0 comments - [Google Agent Development Kit for Kotlin Reaches Feature Parity with Python, Supports On-Device AI](https://daily.dev/posts/google-agent-development-kit-for-kotlin-reaches-feature-parity-with-python-supports-on-device-ai-49dqxbxv2) · InfoQ · 0 upvotes · 0 comments --- Tags: [#android](https://daily.dev/tags/android), [#nlp](https://daily.dev/tags/nlp), [#tensorflow](https://daily.dev/tags/tensorflow) [View this post on daily.dev](https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"ML Kit expands into NLP with Language Identification and Smart Reply","url":"https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds"},"datePublished":"2026-08-23T12:18:48.448Z","dateModified":"2026-08-23T12:24:27.540Z","description":"Firebase's ML Kit adds two new on-device NLP APIs: Language Identification and Smart Reply. Language Identification recognizes 110 languages, typically needs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7ed721de96163685d26ab7e314be3ebc?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7ed721de96163685d26ab7e314be3ebc?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Firebase","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Firebase","logo":"https://media.daily.dev/image/upload/s--i395oqZH--/f_auto,q_auto/v1787487448/logos/firebase-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/firebase-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"android,nlp,tensorflow","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Firebase","item":"https://daily.dev/sources/firebase-blog"},{"@type":"ListItem","position":3,"name":"ML Kit expands into NLP with Language Identification and Smart Reply"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ml-kit-expands-into-nlp-with-language-identification-and-smart-reply-ahxbo6wds#faq","mainEntity":[{"@type":"Question","name":"How fast is ML Kit's Language Identification API and how many languages does it support?","acceptedAnswer":{"@type":"Answer","text":"ML Kit's Language Identification API recognizes 110 different languages and typically only needs a few words of text to make an accurate determination. It responds within 1 to 2 milliseconds across both iOS and Android phones, running fully on-device. If no language can be confidently identified, it returns a BCP-47 code of 'und' for undetermined. Developers picking on-device NLP tools can track new ML Kit API releases like this on daily.dev."}},{"@type":"Question","name":"How does the Smart Reply API in ML Kit generate chat reply suggestions?","acceptedAnswer":{"@type":"Answer","text":"Smart Reply uses a machine-learned model executed with TensorFlow Lite, built on SentencePiece text encoding and Transformer architecture, running entirely on-device without sending message history to a server. It generates suggestions based on the last 10 messages in a conversation, works with as few as one prior message, and includes a sensitive-topic detector to avoid replying to profanity or personal hardship. It launches with English support only. Teams weighing on-device versus cloud NLP for chat features can follow API updates like this on daily.dev."}},{"@type":"Question","name":"What platforms and OS versions support Firebase ML Kit's Smart Reply and Language Identification APIs?","acceptedAnswer":{"@type":"Answer","text":"Both APIs run fully on-device and are available on iOS 9.0 and higher and Android 4.1 and higher, as part of the latest ML Kit SDK. They are called with simple function calls, such as suggestReplies() for Smart Reply and identifyLanguage() for Language Identification, both using Kotlin in the documented examples. Mobile developers integrating on-device ML SDKs can keep up with platform requirements like these on daily.dev."}}]} ```