{"id":22440,"date":"2025-10-27T17:19:26","date_gmt":"2025-10-27T13:19:26","guid":{"rendered":"https:\/\/krisp.ai\/blog\/?p=22440"},"modified":"2025-11-03T13:35:16","modified_gmt":"2025-11-03T09:35:16","slug":"krisp-turn-taking-v2-voice-ai-viva-sdk","status":"publish","type":"post","link":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/","title":{"rendered":"Audio-Only Turn-Taking Model v2"},"content":{"rendered":"<h2>Introducing Krisp\u2019s Turn-Taking v2<!-- notionvc: 2f14aca3-cf08-4499-a128-4a13c287c66c --><\/h2>\n<p>We\u2019ve already discussed the challenges of turn-taking in conversational AI in <a href=\"https:\/\/krisp.ai\/blog\/turn-taking-for-voice-ai\/\">this blog post<\/a>.<br \/>\nNow, we\u2019re excited to announce our newest <strong>Turn-Taking model<\/strong>, available as part of <a href=\"https:\/\/krisp.ai\/blog\/krisp-launches-viva-sdk-and-surpasses-1b-minutes-of-voice-ai-processing-per-month-milestone\/\">Krisp\u2019s VIVA SDK<\/a>.<\/p>\n<p>In this article, we\u2019ll walk through the technology behind the new model and share our latest testing results. The new generation of models is more streamlined than ever\u2014making it simple to integrate <strong>Voice Isolation<\/strong>, <strong>Turn-Taking<\/strong>, and <strong>VAD<\/strong> into your Voice AI pipelines.<\/p>\n<p>If you\u2019d like to see how Krisp\u2019s VIVA SDK can enhance your Voice AI agent experience, apply now from our <a href=\"#\">Developers page<\/a>.<\/p>\n<hr \/>\n<h2>How the New Model Works<\/h2>\n<p>Our latest model predicts <strong>End-of-Turns<\/strong> using only audio input\u2014perfect for real-time conversational systems like human-bot interactions.<\/p>\n<p>Compared to v1, <strong><em>krisp-viva-tt-v2<\/em><\/strong>\u00a0represents a major step forward. It was trained on a more diverse and better-structured dataset, with richer data augmentations that help the model perform more reliably in real-world conditions.<\/p>\n<hr \/>\n<h2>Key Improvements in v2<\/h2>\n<ul>\n<li>Greater robustness in noisy environments<\/li>\n<li>Higher accuracy when paired with Krisp\u2019s Voice Isolation models<\/li>\n<li>Faster and more stable turn detection in live conversations<\/li>\n<\/ul>\n<hr \/>\n<h2>Testing Results<\/h2>\n<h3>Testing on Clean Audio<\/h3>\n<p>We evaluated both model versions on ~1800 audio samples from real conversations, including ~1000 \u201chold\u201d cases and ~800 \u201cshift\u201d cases, with mild background noise.<\/p>\n<p>Although the numerical difference between versions is small on this clean dataset, the results show that <strong>v2<\/strong> achieves faster mean shift prediction time at the same false positive rate.<\/p>\n<table style=\"border-collapse: collapse; width: 100%; text-align: left;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Balanced Accuracy<\/th>\n<th>AUC<\/th>\n<th>F1 Score<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>krisp-viva-tt-v1<\/td>\n<td>0.82<\/td>\n<td>0.89<\/td>\n<td>0.804<\/td>\n<\/tr>\n<tr>\n<td><strong>krisp-viva-tt-v2<\/strong><\/td>\n<td><strong>0.823<\/strong><\/td>\n<td><strong>0.904<\/strong><\/td>\n<td><strong>0.813<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><img loading=\"lazy\" class=\"alignnone size-full wp-image-22469\" src=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_.png\" alt=\"\" width=\"1200\" height=\"600\" srcset=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_.png 1200w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_-300x150.png 300w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_-380x190.png 380w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_-768x384.png 768w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/1_-600x300.png 600w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" \/><\/p>\n<blockquote><p><strong>Insight:<\/strong> Even in clean audio conditions, <em>krisp-viva-tt-v2<\/em> offers slightly better prediction stability and overall performance.<\/p><\/blockquote>\n<hr \/>\n<h3>Testing on Noisy Audio<\/h3>\n<p>Next, we evaluated the models on noisy audio mixes at 5 dB, 10 dB, and 15 dB noise levels. Two scenarios were tested:<\/p>\n<ol>\n<li>Directly on the noisy dataset<\/li>\n<li>On the same dataset after processing through the Krisp VIVA Voice Isolation model<\/li>\n<\/ol>\n<p>In both scenarios, <strong>krisp-viva-tt-v2<\/strong> consistently outperformed <strong>v1<\/strong>.<\/p>\n<table style=\"border-collapse: collapse; width: 100%; text-align: left;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Balanced Accuracy<\/th>\n<th>AUC<\/th>\n<th>F1 Score<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>krisp-viva-tt-v1<\/td>\n<td>0.723<\/td>\n<td>0.799<\/td>\n<td>0.71<\/td>\n<\/tr>\n<tr>\n<td><strong>krisp-viva-tt-v2<\/strong><\/td>\n<td><strong>0.768<\/strong><\/td>\n<td><strong>0.842<\/strong><\/td>\n<td><strong>0.757<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><img loading=\"lazy\" class=\"alignnone size-full wp-image-22470\" src=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_.png\" alt=\"\" width=\"1200\" height=\"600\" srcset=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_.png 1200w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_-300x150.png 300w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_-380x190.png 380w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_-768x384.png 768w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/2_-600x300.png 600w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" \/><\/p>\n<p>&nbsp;<\/p>\n<blockquote><p><strong>Insight:<\/strong> <em>krisp-viva-tt-v2<\/em> delivers up to a 6% improvement in F1 score under noisy conditions, demonstrating greater resilience in real-world environments.<\/p><\/blockquote>\n<hr \/>\n<h3>Testing After Noise and Voice Removal<\/h3>\n<p>Finally, we tested both models on the same noisy dataset <strong>after applying background noise and voice removal<\/strong> with the <strong><em>krisp-viva-tel-v2<\/em><\/strong> model.<\/p>\n<table style=\"border-collapse: collapse; width: 100%; text-align: left;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Balanced Accuracy<\/th>\n<th>AUC<\/th>\n<th>F1 Score<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>krisp-viva-tt-v1<\/td>\n<td>0.787<\/td>\n<td>0.854<\/td>\n<td>0.775<\/td>\n<\/tr>\n<tr>\n<td><strong>krisp-viva-tt-v2<\/strong><\/td>\n<td><strong>0.816<\/strong><\/td>\n<td><strong>0.885<\/strong><\/td>\n<td><strong>0.808<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><img loading=\"lazy\" class=\"alignnone size-full wp-image-22471\" src=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_.png\" alt=\"\" width=\"1200\" height=\"600\" srcset=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_.png 1200w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_-300x150.png 300w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_-380x190.png 380w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_-768x384.png 768w, https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/3_-600x300.png 600w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" \/><\/p>\n<blockquote><p><strong>Insight:<\/strong> When combined with Krisp\u2019s Voice Isolation technology, <em>v2<\/em> achieves even greater accuracy and stability.<\/p><\/blockquote>\n<hr \/>\n<h2>Conclusion<\/h2>\n<p>The new <strong>krisp-viva-tt-v2<\/strong> model marks a significant leap forward in real-time conversation handling for Voice AI. With improved robustness against noise and smoother integration with Krisp\u2019s other models, developers can now build <strong>faster, smarter, and more natural-sounding conversational agents<\/strong>.<\/p>\n<p>Explore the <a href=\"http:\/\/krisp.ai\/developers\">VIVA SDK<\/a> today and see how Krisp\u2019s advanced models can elevate your Voice AI experience.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Introducing Krisp\u2019s Turn-Taking v2 We\u2019ve already discussed the challenges of turn-taking in conversational AI in this blog post. Now, we\u2019re excited to announce our newest Turn-Taking model, available as part of Krisp\u2019s VIVA SDK. In this article, we\u2019ll walk through the technology behind the new model and share our latest testing results. The new generation [&hellip;]<\/p>\n","protected":false},"author":71,"featured_media":22445,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"two_page_speed":[]},"categories":[417,421,456],"tags":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v24.2 (Yoast SEO v23.6) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Audio-Only Turn-Taking Model v2 - Krisp<\/title>\n<meta name=\"description\" content=\"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Audio-Only Turn-Taking Model v2 - Krisp\" \/>\n<meta property=\"og:description\" content=\"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\" \/>\n<meta property=\"og:site_name\" content=\"Krisp\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/krispHQ\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-10-27T13:19:26+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-03T09:35:16+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"700\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Krisp Engineering Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@krispHQ\" \/>\n<meta name=\"twitter:site\" content=\"@krispHQ\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\"},\"author\":{\"name\":\"Krisp Engineering Team\",\"@id\":\"https:\/\/krisp.ai\/blog\/#\/schema\/person\/e9f59158d89de3002958d323d2e788f5\"},\"headline\":\"Audio-Only Turn-Taking Model v2\",\"datePublished\":\"2025-10-27T13:19:26+00:00\",\"dateModified\":\"2025-11-03T09:35:16+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\"},\"wordCount\":459,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/krisp.ai\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png\",\"articleSection\":[\"Company\",\"Engineering Blog\",\"SDK\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\",\"url\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\",\"name\":\"Audio-Only Turn-Taking Model v2 - Krisp\",\"isPartOf\":{\"@id\":\"https:\/\/krisp.ai\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png\",\"datePublished\":\"2025-10-27T13:19:26+00:00\",\"dateModified\":\"2025-11-03T09:35:16+00:00\",\"description\":\"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.\",\"breadcrumb\":{\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage\",\"url\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png\",\"contentUrl\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png\",\"width\":1000,\"height\":700},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/krisp.ai\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Audio-Only Turn-Taking Model v2\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/krisp.ai\/blog\/#website\",\"url\":\"https:\/\/krisp.ai\/blog\/\",\"name\":\"Krisp\",\"description\":\"Blog\",\"publisher\":{\"@id\":\"https:\/\/krisp.ai\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/krisp.ai\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/krisp.ai\/blog\/#organization\",\"name\":\"Krisp\",\"url\":\"https:\/\/krisp.ai\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/krisp.ai\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2024\/10\/K.png\",\"contentUrl\":\"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2024\/10\/K.png\",\"width\":696,\"height\":696,\"caption\":\"Krisp\"},\"image\":{\"@id\":\"https:\/\/krisp.ai\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/krispHQ\/\",\"https:\/\/x.com\/krispHQ\",\"https:\/\/www.linkedin.com\/company\/krisphq\/\",\"https:\/\/www.youtube.com\/channel\/UCAMZinJdR9P33fZUNpuxXtg\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/krisp.ai\/blog\/#\/schema\/person\/e9f59158d89de3002958d323d2e788f5\",\"name\":\"Krisp Engineering Team\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/krisp.ai\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/26475ad8219056696662f819691ee49d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/26475ad8219056696662f819691ee49d?s=96&d=mm&r=g\",\"caption\":\"Krisp Engineering Team\"},\"url\":\"https:\/\/krisp.ai\/blog\/author\/eng-team\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Audio-Only Turn-Taking Model v2 - Krisp","description":"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/","og_locale":"en_US","og_type":"article","og_title":"Audio-Only Turn-Taking Model v2 - Krisp","og_description":"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.","og_url":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/","og_site_name":"Krisp","article_publisher":"https:\/\/www.facebook.com\/krispHQ\/","article_published_time":"2025-10-27T13:19:26+00:00","article_modified_time":"2025-11-03T09:35:16+00:00","og_image":[{"width":1000,"height":700,"url":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png","type":"image\/png"}],"author":"Krisp Engineering Team","twitter_card":"summary_large_image","twitter_creator":"@krispHQ","twitter_site":"@krispHQ","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#article","isPartOf":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/"},"author":{"name":"Krisp Engineering Team","@id":"https:\/\/krisp.ai\/blog\/#\/schema\/person\/e9f59158d89de3002958d323d2e788f5"},"headline":"Audio-Only Turn-Taking Model v2","datePublished":"2025-10-27T13:19:26+00:00","dateModified":"2025-11-03T09:35:16+00:00","mainEntityOfPage":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/"},"wordCount":459,"commentCount":0,"publisher":{"@id":"https:\/\/krisp.ai\/blog\/#organization"},"image":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage"},"thumbnailUrl":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png","articleSection":["Company","Engineering Blog","SDK"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/","url":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/","name":"Audio-Only Turn-Taking Model v2 - Krisp","isPartOf":{"@id":"https:\/\/krisp.ai\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage"},"image":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage"},"thumbnailUrl":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png","datePublished":"2025-10-27T13:19:26+00:00","dateModified":"2025-11-03T09:35:16+00:00","description":"Krisp\u2019s new Turn-Taking v2 model improves real-time conversational accuracy for Voice AI systems. Discover how it outperforms v1 with higher accuracy, faster turn detection, and stronger noise resilience \u2014 now available in the VIVA SDK.","breadcrumb":{"@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#primaryimage","url":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png","contentUrl":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2025\/10\/Turn-taking-blog-visual2.png","width":1000,"height":700},{"@type":"BreadcrumbList","@id":"https:\/\/krisp.ai\/blog\/krisp-turn-taking-v2-voice-ai-viva-sdk\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/krisp.ai\/blog\/"},{"@type":"ListItem","position":2,"name":"Audio-Only Turn-Taking Model v2"}]},{"@type":"WebSite","@id":"https:\/\/krisp.ai\/blog\/#website","url":"https:\/\/krisp.ai\/blog\/","name":"Krisp","description":"Blog","publisher":{"@id":"https:\/\/krisp.ai\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/krisp.ai\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/krisp.ai\/blog\/#organization","name":"Krisp","url":"https:\/\/krisp.ai\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/krisp.ai\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2024\/10\/K.png","contentUrl":"https:\/\/krisp.ai\/blog\/wp-content\/uploads\/2024\/10\/K.png","width":696,"height":696,"caption":"Krisp"},"image":{"@id":"https:\/\/krisp.ai\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/krispHQ\/","https:\/\/x.com\/krispHQ","https:\/\/www.linkedin.com\/company\/krisphq\/","https:\/\/www.youtube.com\/channel\/UCAMZinJdR9P33fZUNpuxXtg"]},{"@type":"Person","@id":"https:\/\/krisp.ai\/blog\/#\/schema\/person\/e9f59158d89de3002958d323d2e788f5","name":"Krisp Engineering Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/krisp.ai\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/26475ad8219056696662f819691ee49d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/26475ad8219056696662f819691ee49d?s=96&d=mm&r=g","caption":"Krisp Engineering Team"},"url":"https:\/\/krisp.ai\/blog\/author\/eng-team\/"}]}},"_links":{"self":[{"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/posts\/22440"}],"collection":[{"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/users\/71"}],"replies":[{"embeddable":true,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/comments?post=22440"}],"version-history":[{"count":10,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/posts\/22440\/revisions"}],"predecessor-version":[{"id":22472,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/posts\/22440\/revisions\/22472"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/media\/22445"}],"wp:attachment":[{"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/media?parent=22440"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/categories?post=22440"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/krisp.ai\/blog\/wp-json\/wp\/v2\/tags?post=22440"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}