Veriwire
← Back to the wire

Gemini 3.8 text-to-speech says hello

AnnouncementModelSep 23, 2026

Google announced two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. Gemini 3.8 Flash TTS ranked first on Hume AI's Voice Design Benchmark with a score of 71.4. The models support voice creation from natural language prompts, a library of over 2,000 voices, and voice replication from 30-second samples with consent verification and SynthID watermarking. They support more than 100 languages and are available now in Google AI Studio.

Receipt № 20571 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01high
blog.googleOfficialhttps://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/
PRIMARY
GoogleCompanyGemini 3.8 Flash TTSModelGemini 3.8 Flash-Lite TTSModel3.5 Live TranslateModel3.5 TranscribeModel3.8 LiveModel3.8 Live Extended ThinkingModel

Related

Sep 22Introducing GPT-6 Sol and LunaSep 23**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**Sep 24GitHub - inlevel9-com/Vons
Canonical: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/