Gemini 3.8 Flash and Flash-Lite TTS: new text-to-speech models
Melvin Vivas · X post · 2026-09-24 · Open on X
Topics: Industry Trends & Job Market, AI Dev Tools & Productivity · Level: beginner
Summary
Melvin Vivas shares Google's launch of the Gemini 3.8 Flash and Flash-Lite TTS text-to-speech models. Listed features include voice design, 2,000+ production-ready voices, voice replication, support for 100 languages, upcoming voice remixing, and the #1 spot on Hume AI's voice benchmarks.
Key points
- Two new TTS models: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS.
- A new voice design experience.
- 2,000+ production-ready voices.
- Voice replication, plus voice remixing coming soon.
- Support for 100 languages.
- Claimed #1 spot on Hume AI's voice benchmarks.
Resources mentioned
- Gemini 3.8 Flash TTS · tool · blog.google · check price
Google's text-to-speech model with voice design, voice replication and support for 100 languages. - Gemini 3.8 Flash-Lite TTS · tool · ai.google.dev · check price
A lighter version of Google's Gemini 3.8 TTS model. - Hume AI voice benchmarks · website · hume.ai · free
Hume AI's benchmarks for comparing voice and TTS models.
Try this
- Build a multilingual voice app or narrator using Gemini 3.8 Flash TTS voices.
More in Industry Trends & Job Market
- On-Device AI: Running Gemma 4 E2B Offline on an iPhone with LiteRT
- Unsloth passes 500M model downloads on Hugging Face
- ChatGPT Voice Update: Plugins, Model Switching and ChatGPT Work
- Space Bunny Alpha: stealth 1M-context flash model on OpenRouter
- Qwen-Audio-3.1: Alibaba's Five-Model Audio Stack
- DeepSWE results: GPT-6 Sol slightly below GPT-5.6 Sol, but cheaper