Gemini 3.1 Flash TTS adds inline direction for generated speech

Audio tags steer pacing and delivery across more than 70 languages.

Capvise MediaEvent 15 Apr 2026Published 15 Oct 20261 min read

Photo: Earlier or representative hardware photograph: Google Pixel 9 Pro XL (back). The pictured model differs from the product discussed in this report. Credit: D.328, “Google Pixel 9 Pro XL (back).jpg,” Wikimedia Commons, CC BY-SA 4.0. Adapted by resizing and WebP re-encoding. · CC BY-SA 4.0 · Resized for web delivery

Directing the delivery

Google introduced Gemini 3.1 Flash TTS on 15 April, adding audio tags that let developers direct speaking style, pace and expression within the input text. Preview access opened through the Gemini API, AI Studio and Vertex AI, with a further route for Workspace users in Google Vids.

The model supports more than 70 languages and multi-speaker dialogue. AI Studio controls include scene direction, speaker profiles and exportable parameters, allowing a configuration to move from a prototype into API code. Google says generated audio carries SynthID. These controls make delivery more adjustable; they do not establish that a synthetic speaker represents a real person or that every pronunciation is correct. Publishers still need to review names, numbers and the intended reading.