Google Launches Gemini 3.1 Flash TTS API with Natural Language Voice Direction and Multi-Speaker Dialogue
By
Rohan Chaubey
Yesterday's bagel. Skim it, don't savour it.
Summary
Google has launched a text-to-speech API called Gemini 3.1 Flash TTS that features natural language voice direction, inline audio tags, multi-speaker dialogue support, and compatibility with over 70 languages. The API is designed for developers building voice agents, dubbing tools, and AI content products through Google's Gemini API and Vertex AI platforms.
Key quotes
· 3 pulledGoogle's TTS API with inline audio tags, multi-speaker dialogue, and 70+ language support.
For developers building voice agents, dubbing tools, or AI content products via the Gemini API and Vertex AI.
Text-to-speech API with natural language voice direction - Google Gemini 3.1 Flash TTS
You might also wanna read
Google Expands Gemini AI with Audio File Support, New Language Capabilities, and Enhanced NotebookLM Features
Google announced three major updates to its Gemini AI products: the Gemini app now supports audio file uploads (up to 10 minutes for free us
The Verge·8mo ago
Google Adds AI Music Generation to Gemini App Using DeepMind's Lyria 3 Model
Google has integrated DeepMind's Lyria 3 AI audio model into its Gemini app, enabling users to generate 30-second AI music tracks based on t
The Verge·3mo ago
Google Docs Adds AI-Powered Audio Generation Feature Using Gemini
Google is rolling out a new AI-powered feature in Google Docs that allows users to generate audio versions of their documents using Gemini A
The Verge·9mo ago
Google Launches Gemini 2.5 Flash Image: Advanced AI Image Generation and Editing Model
Google has launched Gemini 2.5 Flash Image, a new state-of-the-art image generation and editing model that enables blending multiple images,
developers.googleblog.com·9mo ago
Google launches Gemini 3.5 with agentic AI capabilities and 2M token context window
Google has released Gemini 3.5, a new series of AI models that combine frontier-level intelligence with the ability to take actions in the r
blog.google·5d agoGoogle launches Gemini 3.5 with agentic AI capabilities and 2M token context window
Google has released Gemini 3.5, a new series of AI models that combine frontier-level intelligence with the ability to take actions in the r
blog.google·5d ago
Google Releases Gemini 3 Pro AI Model with Audio Transcription and New Benchmark Performance
Google has released Gemini 3 Pro, an upgraded version of Gemini 2.5 that brings it to parity with leading rival AI models. The article provi