https://tech.ldas.jp/en/tags/voice-cloning/Recent content in Voice-Cloning on Digital Archive Systems Tech BlogHugoenThu, 30 Apr 2026 06:00:00 +0900https://tech.ldas.jp/en/posts/elevenlabs-v3-japanese-tech-narration/Thu, 30 Apr 2026 06:00:00 +0900https://tech.ldas.jp/en/posts/elevenlabs-v3-japanese-tech-narration/<blockquote> <p>This article is co-authored with generative AI. While I have cross-checked facts against official documentation where possible, errors may remain. Please verify primary sources before making important decisions.</p></blockquote> <p>I ran an experiment to narrate technical blog articles with a synthetic voice cloned from my own speech. The audio is generated with <a href="https://elevenlabs.io/">ElevenLabs</a> Voice Cloning + the v3 model (<code>eleven_v3</code>, in alpha at the time of writing).</p> <p>This post records an A/B comparison of v2 (<code>eleven_multilingual_v2</code>) and v3 on identical Japanese narration material, together with operational observations.</p>