- What changed
- Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS models that can clone a voice from 30 seconds of audio.
- Why you should care
- Voice cloning capabilities integrated into standard developer APIs lower the barrier to entry for custom synthetic media.
- Your move
- Watch. Monitor adoption and compliance patterns for short-sample voice cloning.
- What to watch next
- Independent developer benchmarks evaluating the audio quality and safety guardrails of the new Gemini text-to-speech models.
- Event
- release
- Event date
- Sep 23, 2026
- Relevant to
- General AI readers
