{"author":{"name":"Lana Zhang","slug":"lana-zhang","article_count":2,"latest_published_at":"2026-05-19T16:18:00.864+00:00","profile_url":"https://vff.ai/authors/lana-zhang","api_url":"https://vff.ai/api/authors/lana-zhang"},"articles":[{"slug":"scalable-voice-agent-design-with-amazon-nova-sonic-multi-agent-tools-and-session","title":"AWS Details Modular Voice Agent Design for Production Scale","url":"https://vff.ai/article/2026/05/19/scalable-voice-agent-design-with-amazon-nova-sonic-multi-agent-tools-and-session","content_type":"aggregated_news","summary":"Amazon has published a technical guide on building scalable voice agents using Nova Sonic, a speech-to-speech foundation model, combined with Bedrock AgentCore Runtime and the open source Strands Agents framework. The post outlines three architectural patterns: tool-driven agents, sub-agents acting as tools, and session segmentation strategies that decompose large assistants into specialized, reusable components. The approach addresses common production challenges like latency, real-time audio management, and multi-agent coordination by leveraging serverless hosting, bidirectional WebSocket streaming, microVM-level isolation, and persistent memory across sessions.","published_at":"2026-05-19T16:18:00.864+00:00","updated_at":"2026-05-20T02:15:09.656235+00:00","source":{"url":"https://aws.amazon.com/blogs/machine-learning/scalable-voice-agent-design-with-amazon-nova-sonic-multi-agent-tools-and-session-segmentation/","name":"AWS Machine Learning Blog"},"featured_image":{"url":"https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/08/ML-20826-1.png","alt":null},"categories":[{"name":"Voice & Video AI","slug":"voice-video-ai"},{"name":"AI Agents","slug":"ai-agents"},{"name":"Infrastructure","slug":"infrastructure"},{"name":"AWS","slug":"aws"}]},{"slug":"migrating-a-text-agent-to-a-voice-assistant-with-amazon-nova-2-sonic","title":"Text Agents and Voice Agents Are Different Problems","url":"https://vff.ai/article/2026/04/29/migrating-a-text-agent-to-a-voice-assistant-with-amazon-nova-2-sonic","content_type":"aggregated_news","summary":"AWS published guidance on migrating text-based AI agents to voice assistants using Amazon Nova 2 Sonic, emphasizing that the two require fundamentally different architectural approaches. The post details key differences across user input handling, response style, latency requirements, turn-taking mechanics, and transport protocols, then provides design patterns and a reusable skill for developers to automate the conversion process. Voice agents demand real-time bidirectional streaming, ultra-low latency, natural turn-taking with interruption support, and concise spoken responses, whereas text agents tolerate higher latency and deliver rich formatted content.","published_at":"2026-04-29T13:22:46.209+00:00","updated_at":"2026-04-29T13:22:46.734143+00:00","source":{"url":"https://aws.amazon.com/blogs/machine-learning/migrating-a-text-agent-to-a-voice-assistant-with-amazon-nova-2-sonic/","name":"AWS Machine Learning Blog"},"featured_image":{"url":"https://d2908q01vomqb2.cloudfront.net/da4b9237bacccdf19c0760cab7aec4a8359010b0/2024/11/20/Bedrock-Nova-feat-img-1260x630.png","alt":null},"categories":[{"name":"Voice & Video AI","slug":"voice-video-ai"},{"name":"AI Agents","slug":"ai-agents"},{"name":"AWS","slug":"aws"},{"name":"Coding / Dev Tools","slug":"coding-dev-tools"}]}]}