Gemini 3.1 Flash TTS

2026-04-15 · Source: Simon Willison's Weblog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Google released Gemini 3.1 Flash TTS on April 15, 2026, a new text-to-speech model accessible via the standard Gemini API using the `gemini-3.1-flash-tts-preview` model ID. This model uniquely allows for audio generation directed by detailed prompts, which can include "AUDIO PROFILE," "THE SCENE," "DIRECTOR'S NOTES" (covering style, dynamics, pace, and accent), "SAMPLE CONTEXT," and the "TRANSCRIPT." The prompting guide provides an example demonstrating how to specify vocal characteristics like a "Vocal Smile," high projection, energetic pace, and specific regional accents such as Brixton, Newcastle, or Exeter. The model outputs audio files, and a UI for experimentation was developed using Gemini 3.1 Pro.

Key takeaway

For AI Product Managers or Machine Learning Engineers developing audio experiences, Gemini 3.1 Flash TTS offers unprecedented control over generated speech. You should explore its detailed prompting capabilities to create highly customized and expressive voiceovers, ensuring your applications can deliver specific regional accents and nuanced vocal styles without extensive post-processing.

Key insights

Gemini 3.1 Flash TTS offers highly granular, prompt-driven control over speech generation, including accents and vocal styles.

Principles

• Detailed contextual prompting enhances TTS output.
• Specific vocal characteristics are controllable via prompt tags.

Method

Users define audio profiles, scene context, director's notes (style, pace, accent), and sample context within a structured prompt to guide the Gemini 3.1 Flash TTS model's audio generation.

In practice

• Experiment with "Vocal Smile" and accent tags.
• Use "DIRECTOR'S NOTES" for precise vocal control.

Topics

• Gemini 3.1 Flash TTS
• Text-to-Speech Model
• Prompt Engineering
• Audio Generation
• Gemini API

Best for: Machine Learning Engineer, AI Product Manager, AI Engineer, NLP Engineer, Prompt Engineer

Related on AIssential

• Gemini 3.1 Flash TTS: the next generation of expressive AI speech — Gemini 3.1 Flash TTS offers granular control over AI speech through natural language audio tags and SynthID watermarking.
• Gemini 3.1 Flash TTS — Google's Gemini 3.1 Flash TTS tool offers customizable, multi-speaker text-to-speech with directorial tags.
• Google Just Handed You a Voice Director’s Chair for Free With Flash 3.1 TTS — Gemini 3.1 Flash TTS offers unprecedented control over synthesized speech through extensive audio tags and presets.
• Build Human-Like AI Voice App with Gemini 3.1 Flash TTS — Gemini 3.1 Flash TTS offers advanced emotional and multi-character voice direction, setting a new benchmark for expressive AI speech.
• Gemini 3.1 Flash TTS: the next generation of expressive AI speech — Gemini 3.1 Flash TTS offers granular control over AI speech through natural language audio tags and high-quality, cost-effective generation.
• Gemini Streaming TTS: How Developers Can Make AI Voice Apps Feel Instant — Streaming TTS shifts AI voice app design from total generation time to time to first audio and smooth playback.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Simon Willison's Weblog.