Skip to content
Google·

🗣️Google Unveils Gemini 3.8 Flash TTS and Flash-Lite TTS

New Gemini models for richer audio experiences

TL;DR

Google introduces Gemini 3.8 Flash TTS and Flash-Lite TTS, offering deep creative direction and high-volume scalability. These models excel in expressive audio creation and support over 100 languages.

Google just dropped Gemini 3.8 Flash TTS and Flash-Lite TTS, two new text-to-speech models designed for creators, developers, and enterprises. Flash TTS is built for deep creative direction, enabling the creation of bespoke voices from scratch with precise control over voice characteristics. Flash-Lite TTS, on the other hand, is optimized for high-volume, cost-efficient scale. Both models support over 100 languages and dialects, making them a game changer for multilingual voice experiences. If you're working on voice-based projects, these new models offer a significant boost in expressiveness and scalability.

Google Unveils Gemini 3.8 Flash TTS and Flash-Lite TTS — Google

Key Points

1

Gemini 3.8 Flash TTS supports over 100 languages and dialects, enabling multilingual voice experiences.

2

Flash TTS secured the #1 overall spot on Hume AI's Voice Design Benchmark (71.4) and led in accent modeling (60.8).

3

Flash TTS can create bespoke voices from scratch by customizing role, accent, and voice characteristics across 100+ languages.

4

Flash TTS can generate voices from a 30-second audio sample or a voice used with consent, ensuring authenticity.

5

Flash TTS maintains high voice quality and natural pacing across hours of continuous audio with minimal drift.

Why It Matters

If you're working on voice-based projects, Gemini 3.8 Flash TTS and Flash-Lite TTS offer a significant boost in expressiveness and scalability. Flash TTS supports over 100 languages, enabling multilingual voice experiences. Flash-Lite TTS is optimized for high-volume, cost-efficient scale, making it ideal for large-scale deployments. Both models secure top positions in key global languages in blind human preference evaluations.

googlegeminitext-to-speechmultilingualvoice-experiences

Comments

Subscribe to join the conversation...

Be the first to comment

Enjoyed this article?

Get it daily. 7am. Free. Reads in 5 minutes.

Join 3,490 builders reading daily.

Also get