Google Releases Gemini 3.8 Flash TTS and Flash-Lite TTS With Prompt-Based Voice Design
Google launched Gemini 3.8 Flash TTS and Flash-Lite TTS with prompt-based voice design, 2,000+ voices, and consent-gated voice replication via API.
Google released Gemini 3.8 Flash TTS (creative direction, character voices) and Flash-Lite TTS (high-volume, cost-efficient production) through the Gemini API and Google AI Studio, API-only with no open weights. Flash TTS generates new voices from text prompts across 100+ languages and dialects, offers a 2,000+ voice library (up from 30), and ranks first on Hume AI's Voice Design Benchmark with 71.4. Voice replication requires a 30-second sample plus a matching verbal consent recording, and all output carries SynthID watermarking with C2PA credentials for replicated voices.
- Flash TTS ranks #1 on Hume AI Voice Design Benchmark (71.4); Flash-Lite ranks #2 overall quality.
- Voice library expands from 30 to 2,000+ production-ready voices.
- Voice replication requires 30-second sample and verbal consent recording matched to the owner.
- All audio carries SynthID watermark; replicated voices include C2PA credentials.
- API-only rollout; enterprise access via Gemini Enterprise coming soon.
From the original article
4 min read at marktechpost.com
Google has released Gemini 3. 8 Flash TTS and Flash-Lite TTS, 2 new text-to-speech models available now through the Gemini API and Google AI Studio. Flash TTS designs new voices from natural language prompts across 100+ languages.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.