--- title: How I Made My Own Offline Voice Assistant | daily.dev description: A developer built a fully offline voice assistant using four local components: Silero VAD for voice activity detection, faster-whisper for speech-to-text,... canonical: https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How I Made My Own Offline Voice Assistant | daily.dev og:description: A developer built a fully offline voice assistant using four local components: Silero VAD for voice activity detection, faster-whisper for speech-to-text,... og:url: https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw og:image: https://api.daily.dev/og/posts/lVEPhkFkW.png og:image:alt: How I Made My Own Offline Voice Assistant 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. # How I Made My Own Offline Voice Assistant **[Medium](https://daily.dev/sources/medium_js)** · 5 min read · 0 upvotes · 0 comments ## Summary A developer built a fully offline voice assistant using four local components: Silero VAD for voice activity detection, faster-whisper for speech-to-text, Ollama running phi3:mini as the local LLM brain, and Piper TTS for speech output. The key engineering challenge was achieving sub-2-second response latency. Sequential processing caused unacceptable delays, so the author switched to end-to-end streaming where TTS synthesizes and plays each sentence as the LLM generates it. To mask the remaining 2-second hardware delay, a Turn Manager plays conversational filler audio at 300ms and 1 second, making perceived latency feel near-zero. A barge-in feature detects the user's voice in 88ms to interrupt the assistant. A graceful fallback routes to Groq's cloud API if the local model stalls, with a friendly audio error message if both fail. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Build a Fully Local Voice Assistant With Whisper and Ollama](https://daily.dev/posts/build-a-fully-local-voice-assistant-with-whisper-and-ollama-lswpqs4yi) · Medium · 2 upvotes · 0 comments - [I built a local voice assistant that doesn't need the internet, and it actually understands me](https://daily.dev/posts/i-built-a-local-voice-assistant-that-doesn-t-need-the-internet-and-it-actually-understands-me-8kvd4gsfc) · XDA Developers · 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 to Build Your Own Private Voice Assistant: A Step-by-Step Guide Using Open-Source Tools](https://daily.dev/posts/how-to-build-your-own-private-voice-assistant-a-step-by-step-guide-using-open-source-tools-gvm7nqul7) · freeCodeCamp · 5 upvotes · 0 comments - [I gave up on Google for voice control, and my house got smarter instead of dumber](https://daily.dev/posts/i-gave-up-on-google-for-voice-control-and-my-house-got-smarter-instead-of-dumber-8z2fui9lr) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#local-ai](https://daily.dev/tags/local-ai), [#ollama](https://daily.dev/tags/ollama), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#text-to-speech](https://daily.dev/tags/text-to-speech) [View this post on daily.dev](https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw) ```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":"How I Made My Own Offline Voice Assistant","url":"https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw"},"datePublished":"2026-07-22T12:02:09.276Z","dateModified":"2026-07-22T12:04:03.366Z","description":"A developer built a fully offline voice assistant using four local components: Silero VAD for voice activity detection, faster-whisper for speech-to-text,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/770bc6426faa67dfca97adb27097498d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/770bc6426faa67dfca97adb27097498d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-i-made-my-own-offline-voice-assistant-lvephkfkw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"local-ai,ollama,speech-recognition,text-to-speech","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"How I Made My Own Offline Voice Assistant"}]} ```