Google launches Playground to create browser games from text prompts

Google launches Playground to create browser games from text prompts

Ondřej Barták
Ondřej Barták
Entrepreneur and Programmer
8. 10. 2026
1 minutes reading · 10 views
Listen to the article
Audio version of the article
Google launches Playground to create browser games from text prompts

Google Labs launched Playground on Wednesday, an experimental platform that creates browser games from simple text prompts. People without coding knowledge can describe how they want their game to work and look. Access is initially limited to users aged 18 and older in the US.

Choose a genre and bring your own visuals

Creators can begin by choosing a genre, such as trivia or racing, or start a project from scratch. During setup, they select a 2D or 3D game and decide whether it will be a single-player or multiplayer experience.

They then describe the game’s mechanics, gameplay and visual style. Input is not limited to text: users can also upload images, which Playground’s AI turns into game assets matched to the project’s overall art style.

Play on mobile or desktop and share through Explore

Created games can be played on mobile devices and computers. Creators choose how to make their projects available: they can keep them private, share a link or publish them in Playground’s Explore gallery.

Published games can include leaderboards. Creators can also continue editing their projects after releasing them to players.

Access and weekly creation limits

Google plans to expand Playground’s availability to more countries. Browsing the catalog and playing games is free, while game generation uses a weekly token allowance: the free tier offers a limited allocation, and Google One AI subscribers receive higher usage limits.

Google plans Unity Spark integration

Google plans to add Unity Spark integration in a future update. The company says it could expand Playground’s 3D creation capabilities and provide professional-level game mechanics through Unity’s technology.

Advertisement

Content created with help from UpTier.

SEO and GEO on autopilot. UpTier’s multi-agent systems write and optimize content for search engines and AI answers.

Discover UpTier ↗

Category:AI
Did you enjoy this article?
Discover more interesting posts on our blog
Back to blog

Related posts

Microsoft CEO Wants an Emergency Brake for Every AIMicrosoft CEO Wants an Emergency Brake for Every AI
Satya Nadella warns that powerful AI cannot be trusted blindly. Every model should have a human-controlled emergency brake, and companies must assume it could be compromised.
9 min read
13. 10. 2026
Sakana AI and UC Berkeley’s MASS research method trains one model for multiple agent rolesSakana AI and UC Berkeley’s MASS research method trains one model for multiple agent roles
Sakana AI and UC Berkeley released MASS and its open-source implementation. One model solves tasks, revises agent workflows and evaluates results. Their experiments showed gains on research tasks but regressions on software benchmarks.
4 min read
13. 10. 2026
Nvidia Wants to Buy Reflection AI, in Talks to Acquire US Open-Model DeveloperNvidia Wants to Buy Reflection AI, in Talks to Acquire US Open-Model Developer
Nvidia is considering another investment, an acquisition or a technology partnership with startup Reflection AI. Its interest was sparked by Beam, an open model focused on coding and competing with Chinese systems.
3 min read
13. 10. 2026
Přihlaste se k odběru našeho newsletteru
Zůstaňte informováni o nejnovějších příspěvcích, exkluzivních nabídkách, a aktualizacích.
CodedTrip

Operated by CodedTrip LLC, USA.

YouTube
TikTok