← Back to the wire

Gemini 3.1 Flash TTS: New text-to-speech AI model

AnnouncementModelApr 15, 2026

Google announced Gemini 3.1 Flash TTS, an AI speech model with improved quality and expressiveness. The model introduces audio tags that allow users to control vocal style, pace, and delivery through natural language commands across over 70 languages. It is available in Google AI Studio, Vertex AI, and Google Vids. All generated audio is watermarked with SynthID to identify AI-generated content and prevent misinformation.

Receipt № 5131 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

GoogleCompanyGemini 3.1 Flash TTSModel
Canonical: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-tts/