- What changed
- Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS with custom voice replication, emotional direction, and built-in safety watermarking.
- Why you should care
- New expressive text-to-speech models expand options for creating custom character voices and direct scene dialogue using natural language prompts.
- Your move
- Watch. Monitor real-world adoption and performance benchmarks before committing production workloads.
- What to watch next
- Independent benchmark evaluations and developer feedback on audio quality and latency.
- Event
- release
- Event date
- Sep 23, 2026
- Relevant to
- General AI readers
