Gemini 3.8 TTS supports cloning a personal voice from a 20-second recording or designing custom voices with prompts
Original title:With Gemini 3.8 TTS you can replicate your voice or design a completely custom one from a prompt
AI summary
Philipp Schmid introduced that Gemini 3.8 TTS supports cloning a personal voice by recording 20 seconds of speech plus a consent sentence, or designing a fully custom voice with prompts. Once created via API calls, it can be used in any request, with style set through speech_metadata. The author also provided a blog link and a complete operation prompt that can be handed to an agent.
Key Takeaways
- Philipp Schmid introduced that Gemini 3.
- 8 TTS supports cloning a personal voice by recording 20 seconds of speech plus a consent…
- Once created via API calls,it can be used in any request,with style set through speech_metadata.
- The author also provided a blog link and a complete operation prompt that can be handed to an agent.
Quick Facts
- Published
- Updated
- Category
- Tutorials & Tips
- AI score
- 69
原文给出录制片段、API 创建与调用的具体步骤和可复用提示词,方便读者快速试用自己的语音复刻。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Gemini 3.8 TTS supports cloning a personal voice from a 20-second recording or designing custom voices with prompts. September 24, 2026. https://new.nat6.net/en/news/uxeaehlgkymifrlgekbksufhu/