Gemini 3.1 Flash TTS
Source published ·Modelwire updated
Original coverage: Simon Willison ↗·How Modelwire adds context
The development
Google launched Gemini 3.1 Flash TTS, a new text-to-speech model accessible via the Gemini API that accepts natural language prompts to control voice characteristics and output style, expanding multimodal capabilities beyond text generation.
Modelwire’s AI-generated summary of coverage from Simon Willison.
Modelwire analysis
Skeptical readOur AI-generated reading of the wider context and the next developments to watch.
The headline capability here is natural language prompt control over voice characteristics, but Google DeepMind's own announcement (covered the same day) frames this more specifically around 'granular audio tags' for expressive speech synthesis — which is a meaningfully different technical claim than free-form prompting, and the two descriptions don't obviously reconcile.
This release lands in the middle of a busy week of Gemini expansion across modalities. As covered in our story on Gemini pulling from Google Photos for personalized image generation (April 16, The Verge and Ars Technica), Google is clearly pushing Gemini into every media type simultaneously. The pattern is consistent: each announcement extends Gemini's reach into a new output format while keeping developers inside the Gemini API. Whether this reflects genuine multimodal depth or a surface-level expansion strategy is the question none of these individual announcements answer on their own.
Watch whether third-party developers report that the natural language prompt controls actually produce reliably differentiated audio outputs, or whether the 'audio tags' framing in the DeepMind post turns out to be the real interface and the prompt-based description is marketing gloss.
This interpretation is generated from the summary above and the archive coverage cited below. Our methodology · Report an error
Coverage behind this analysis
These archive entries ground the connection in our analysis. They are ordered by source publication date, with links to our coverage and the original sources.
·The Verge — AI
Gemini can now pull from Google Photos to generate personalized images
Google has extended its Personal Intelligence feature to let Gemini generate custom images using the Nano Banana 2 model and data from Google Photos. Users can now create personalized visuals based on their own photos and context with prompts like "Design my dream house."
MentionsGoogle · Gemini 3.1 Flash TTS · Gemini API
How this coverage is produced
Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.
Modelwire summarizes, we don’t republish. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.