Design and replicate voices with Gemini 3.8 Flash TTS
From Google for Developers · · 14 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.
If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.
Description
See how Gemini 3.8 Flash TTS lets you design custom voices from a text prompt and replicate your own voice in Google AI Studio. Google DeepMind’s Thor Schaeff walks through:
*Voice design *Voice replication *Multi-speaker dialogue generation *Building with the Gemini API across 100+ languages *Partner integrations with Agora, LiveKit, Pipecat, and Vercel Try it now at ai.studio/generate-speech. Have questions? Drop them in the comments.
Chapters: 0:00 — Introduction to Gemini TTS 0:27 — Voice replication in Google AI Studio 1:00 — Voice design from a text prompt 2:19 — Using custom voices across multiple languages 4:10 — Using custom voices in the Gemini API 5:44 — Listing and managing voices via the Gemini API 8:58 — Multi-speaker dialogue generation 11:55 — Live podcast demo 12:53 — Gemini 3.8 Flash TTS vs. Flash-Lite TTS 13:34 — Partner integrations with Agora, LiveKit, Pipecat, and Vercel
🔗Resources: Blog → https://goo.gle/4dQZL6c Migration Guide → https://goo.gle/4jzgSNG Prompting Guide → https://goo.gle/4ywvpgQ
Subscribe to Google for Developers → https://goo.gle/developers
Speakers: Thor Schaeff Products Mentioned: Gemini, Google AI Studio