DigestAI news desk

Cut through the AI noise.

Listen
Generative AI & Modelsupdated 4 min read

Google launches Gemini 3.8 Flash and Flash‑Lite text‑to‑speech models

Google added two text‑to‑speech models to its Gemini family: Gemini 3.8 Flash TTS, aimed at deep creative direction and character design, and Gemini 3.8 Flash‑Lite TTS, built for high‑volume, cost‑efficient scaling. Both models let developers and enterprises generate expressive, multilingual speech using natural‑language prompts, with control over pacing, dialect, back‑channeling and…

3 sources primary source

What you can do with it

AI at Work →
Gemini 3.8 Flash TTS by Google

Create custom voiceovers for ads, podcasts, and videos

Generate high-quality, customizable speech from text prompts.

Who for
marketers
Cost
Price not stated
Effort
minutes
Already included in
Google AI Studio

Use it for

  • Voice ads
  • Narrate podcasts
  • Localize videos

Watch out May incur usage fees

What happened · blog.google, Google DeepMind Get more customersMake content faster

Gemini 3.8 Flash TTS in the tool directory

Key points from the news

  • Gemini 3.8 Flash TTS creates new voices from prompts and replicates from a 30‑second sample
  • Library includes 2,000+ production‑ready voices in more than 100 languages and dialects
  • Flash TTS ranked #1 on Hume AI’s Voice Design Benchmark (71.4) and leads accent modeling (60.8)

The Flash model can create new voices from scratch, replicate a voice from a 30‑second sample, and offers an expanding library that already includes more than 2,000 production‑ready voices across over 100 languages and dialects, such as Mexican Spanish and Quebec French. The Flash‑Lite variant focuses on dubbing and large‑scale audio creation. In benchmark tests, Gemini 3.8 Flash TTS ranked #1 on Hume AI’s Voice Design Benchmark with a score of 71.4 and led accent modeling with 60.8, while Flash‑Lite took the #2 spot on the Overall Quality Index. The models are available today through the Gemini API, Google AI Studio, Gemini Notebook and, soon, Gemini Enterprise.

Model page: Gemini 3.8 Flash TTS →

The story so far

3 episodes →
  1. Google launches Gemini 3.8 Flash and Flash‑Lite text‑to‑speech modelsthis story
Full story from Google DeepMind · by Leland Rechis primary sourceOpen source ↗

Gemini 3.8 text-to-speech says hello

Google DeepMind · 23 September 2026

Loading the full article…

This text was published by Google DeepMind and written by Leland Rechis. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

3sources
Topics · follow one to build your own front page
GoogleAgoraLiveKitPipecatVercelHume AIGemini 3.8 Flash TTSGemini 3.8 Flash‑Lite TTS

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Generative AI & Models

All →

Related stories

hot Anthropic releases Claude Opus 5.5 with $4 input and $20 output pricing, claiming 40% lower cost than Opus 5 new Advancing Private AI Compute with secure, server-side memory hot YouTube adds AI draft feedback and dynamic thumbnails to Studio app new HubSpot explains how AEO checkers track brand visibility in AI answer engines hot OpenAI's GPT-6 Astra: Changing Work and Research new Meta unveils Ray‑Ban Meta Gen 3 glasses and Luna audio‑only variant hot Amazon expands Seller Assistant from chatbot to operating system for merchants new Google launches Gemini 3.8 Flash and Flash‑Lite text‑to‑speech models