--- title: Get started with the Interactions API | daily.dev description: Google's Gemini Interactions API is now generally available, offering a unified interface for all Gemini models and agents through a single API call. Key... canonical: https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Get started with the Interactions API | daily.dev og:description: Google's Gemini Interactions API is now generally available, offering a unified interface for all Gemini models and agents through a single API call. Key... og:url: https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg og:image: https://api.daily.dev/og/posts/U52PgglsG.png og:image:alt: Get started with the Interactions API 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. # Get started with the Interactions API **[Google for Developers](https://daily.dev/sources/googledevelopers)** · 8 min read · 0 upvotes · 0 comments ## Summary Google's Gemini Interactions API is now generally available, offering a unified interface for all Gemini models and agents through a single API call. Key features include managed agents, background execution, tool mixing, deep research, and media generation (images via Nano Banana, music via Lyra 3, speech via TTS). The API is stateful, allowing developers to chain interactions using previous interaction IDs. A demo walkthrough shows building a photo editing app using an AI coding agent (Anti-gravity IDE) that accepts image and voice input, transcribes speech, and iteratively edits images while maintaining context across interactions via cached tokens. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the Gemini Interactions API and what does it let you do? It is a unified, generally available API providing a single interface to all Gemini models and agents. It supports synchronous calls, background execution for multi-step agent tasks, mixing custom tools with built-in tools, deep research, and media generation including images via Nano Banana, music via Lyra 3, and speech via TTS. It is also stateful, letting you continue a session by passing a previous interaction ID. _See how developers are already building on the Gemini Interactions API in daily.dev's developer feed._ ### Can Nano Banana take audio as a direct input for image editing? No, Nano Banana currently does not support audio as an input. To edit an image based on a spoken prompt, the audio must first be transcribed to text using the Interactions API (with Gemini 3.5 Flash), and that transcribed text is then passed into the image editing request. _Track workarounds like this as multimodal AI tooling evolves, curated on daily.dev._ ### How does passing a previous interaction ID work when using the Gemini Interactions API for iterative image edits? Instead of resending the original image, you pass the previous interaction ID along with a new prompt, and the API uses cached tokens from that prior interaction to apply the new edit while preserving earlier changes. For example, editing a shirt color after already changing a cap color keeps the cap edit intact without needing to reupload the image. _Follow practical patterns like this for building stateful AI agents on daily.dev._ ## Similar posts on daily.dev - [Getting started with the Gemini Interactions API](https://daily.dev/posts/getting-started-with-the-gemini-interactions-api-ch1poaqr8) · Philipp Schmid · 4 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#genai](https://daily.dev/tags/genai), [#google-gemini](https://daily.dev/tags/google-gemini), [#multimodal](https://daily.dev/tags/multimodal) [View this post on daily.dev](https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg) ```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":"Get started with the Interactions API","url":"https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg"},"datePublished":"2026-07-17T23:30:57.864Z","dateModified":"2026-09-13T19:52:39.125Z","description":"Google's Gemini Interactions API is now generally available, offering a unified interface for all Gemini models and agents through a single API call. Key...","image":"https://i.ytimg.com/vi/iOK1-b_9Dlg/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/iOK1-b_9Dlg/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Google for Developers","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":"Google for Developers","logo":"https://media.daily.dev/image/upload/s--jj3nxRoG--/f_auto/v1725035497/logos/googledevelopers","url":"https://daily.dev/sources/googledevelopers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,genai,google-gemini,multimodal","timeRequired":"PT8M","video":{"@type":"VideoObject","name":"Get started with the Interactions API","description":"Google's Gemini Interactions API is now generally available, offering a unified interface for all Gemini models and agents through a single API call. Key...","thumbnailUrl":"https://i.ytimg.com/vi/iOK1-b_9Dlg/sddefault.jpg","uploadDate":"2026-07-17T23:30:57.864Z","duration":"PT8M","url":"https://api.daily.dev/r/U52PgglsG","embedUrl":"https://www.youtube.com/embed/iOK1-b_9Dlg"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google for Developers","item":"https://daily.dev/sources/googledevelopers"},{"@type":"ListItem","position":3,"name":"Get started with the Interactions API"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/get-started-with-the-interactions-api-u52pgglsg#faq","mainEntity":[{"@type":"Question","name":"What is the Gemini Interactions API and what does it let you do?","acceptedAnswer":{"@type":"Answer","text":"It is a unified, generally available API providing a single interface to all Gemini models and agents. It supports synchronous calls, background execution for multi-step agent tasks, mixing custom tools with built-in tools, deep research, and media generation including images via Nano Banana, music via Lyra 3, and speech via TTS. It is also stateful, letting you continue a session by passing a previous interaction ID. See how developers are already building on the Gemini Interactions API in daily.dev's developer feed."}},{"@type":"Question","name":"Can Nano Banana take audio as a direct input for image editing?","acceptedAnswer":{"@type":"Answer","text":"No, Nano Banana currently does not support audio as an input. To edit an image based on a spoken prompt, the audio must first be transcribed to text using the Interactions API (with Gemini 3.5 Flash), and that transcribed text is then passed into the image editing request. Track workarounds like this as multimodal AI tooling evolves, curated on daily.dev."}},{"@type":"Question","name":"How does passing a previous interaction ID work when using the Gemini Interactions API for iterative image edits?","acceptedAnswer":{"@type":"Answer","text":"Instead of resending the original image, you pass the previous interaction ID along with a new prompt, and the API uses cached tokens from that prior interaction to apply the new edit while preserving earlier changes. For example, editing a shirt color after already changing a cap color keeps the cap edit intact without needing to reupload the image. Follow practical patterns like this for building stateful AI agents on daily.dev."}}]} ```