<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Speech to Speech Translation on VibePapa — Tech from the Boseong River</title>
    <link>https://boseonggang.com/tags/speech-to-speech-translation/</link>
    <description>Recent content in Speech to Speech Translation on VibePapa — Tech from the Boseong River</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 14 Jul 2026 20:49:56 +0900</lastBuildDate>
    <atom:link href="https://boseonggang.com/tags/speech-to-speech-translation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>10 Seconds to Zero: Rebuilding My Translator on Gemini&#39;s Streaming API</title>
      <link>https://boseonggang.com/posts/fifteen-seconds-to-zero-gemini-streaming-translation/</link>
      <pubDate>Tue, 14 Jul 2026 20:49:56 +0900</pubDate>
      <guid>https://boseonggang.com/posts/fifteen-seconds-to-zero-gemini-streaming-translation/</guid>
      <description>My old translation app worked in 5-to-15-second chunks, recording, transcribing, translating, then speaking, then stitching each chunk onto the last. Gemini Live Translate throws that whole pipeline away. Here&amp;#39;s the before-and-after, including the exact WebSocket error that took an evening to figure out.</description>
    </item>
  </channel>
</rss>
