Design and replicate voices with Gemini 3.8 Flash TTS
Channel: Google for Developers
Uploaded:
Duration: PT849S
Read a transcript preview of “Design and replicate voices with Gemini 3.8 Flash TTS” from Google for Developers, uploaded on 2026-10-21.
Transcript preview
Language: English (creator captions)
[0:03] Welcome back. Today we're looking at something that completely shifts what's possible with
[0:10] synthetic speech. Text-to-speech used to mean picking from a handful of preset voices that
[0:16] sounded decent, but never quite personal. That changes today. We're diving into the latest
[0:23] TTS capabilities in Gemini, headlined by two massive upgrades. Voice design and voice replication.
[0:29] -Yes, exactly. So that was my voice that I just
[0:35] replicated here in Google AI Studio from just 20 seconds of audio. So
[0:42] now Gemini-TTS can do all the heavy lifting for me. No of course, just kidding.
[0:49] I'm still here and I'm still here to talk you through the latest features. So what's really cool
[0:55] here is we can replicate our voice right within Google AI Studio. We can also
[1:02] simply generate a new voice using Voice Design. And so we can simply
[1:09] describe the voice that we're looking for. And so for example, I'm not great at Spanish,
[1:15] but I just came back from a fun conference in Argentina. So Argentine
[1:22] podcast host. We’ll do that. And let's design the following voice. High energy,
[1:29] mid-twenties female podcast host with a strong local Buenos Aires
[1:35] Argentine Spanish accent hosting a radio show in Spanish.
[1:42] All right, there we go. And now we can also click and proof my prompt. And so now this will be a
[1:49] bit more detailed. And then we can click Generate Voice. And so now we
[1:56] will get three samples that we can choose fro