--- title: One-Second Voice-to-Voice Latency with Modal, Pipecat,... description: Building a conversational voice AI bot with sub-second response latency using Modal's serverless platform, the Pipecat framework, and open-source models. The... canonical: https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models | daily.dev og:description: Building a conversational voice AI bot with sub-second response latency using Modal's serverless platform, the Pipecat framework, and open-source models. The... og:url: https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop og:image: https://api.daily.dev/og/posts/AeJTKCqop.png og:image:alt: One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models 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. # One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models **[Modal](https://daily.dev/sources/modal_labs)** · 14 min read · 0 upvotes · 0 comments ## Summary Building a conversational voice AI bot with sub-second response latency using Modal's serverless platform, the Pipecat framework, and open-source models. The implementation achieves ~1 second voice-to-voice latency by combining Parakeet STT, Qwen3 LLM with vLLM, and Kokoro TTS. Key optimizations include using Modal Tunnels to bypass the input plane, WebRTC for client connections, regional pinning to minimize network latency, and independent autoscaling of GPU services. The demo includes a RAG-powered assistant for Modal's documentation with structured outputs and animated avatars. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Real-time voice AI low-latency techniques that work](https://daily.dev/posts/real-time-voice-ai-low-latency-techniques-that-work-noffnjl2b) · Netguru · 0 upvotes · 0 comments - [How I built a sub-500ms latency voice agent from scratch](https://daily.dev/posts/how-i-built-a-sub-500ms-latency-voice-agent-from-scratch-neao8lbjr) · Hacker News · 0 upvotes · 0 comments - [How I Made My Own Offline Voice Assistant](https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw) · Medium · 0 upvotes · 0 comments - [How Decagon shipped real-time voice AI on Modal](https://daily.dev/posts/how-decagon-shipped-real-time-voice-ai-on-modal-y0nigfyhy) · Modal · 1 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#real-time-systems](https://daily.dev/tags/real-time-systems), [#voice-ai](https://daily.dev/tags/voice-ai), [#webrtc](https://daily.dev/tags/webrtc) [View this post on daily.dev](https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop) ```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":"One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models","url":"https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop"},"datePublished":"2025-11-04T22:13:07.962Z","dateModified":"2026-03-30T02:12:48.400Z","description":"Building a conversational voice AI bot with sub-second response latency using Modal's serverless platform, the Pipecat framework, and open-source models. The...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/541320873264f1ac7dc894ba522a25ce?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/541320873264f1ac7dc894ba522a25ce?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Modal","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":"Modal","logo":"https://media.daily.dev/image/upload/s--HfKZHzC1--/f_auto/v1750946306/logos/modal_labs","url":"https://daily.dev/sources/modal_labs"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/one-second-voice-to-voice-latency-with-modal-pipecat-and-open-models-aejtkcqop","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,real-time-systems,voice-ai,webrtc","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Modal","item":"https://daily.dev/sources/modal_labs"},{"@type":"ListItem","position":3,"name":"One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models"}]} ```