AI Models
Powered by the Gemini family — transparently
HYR Studio runs on Google DeepMind's Gemini family — and we tell you exactly which model powers what.
Every generation type in HYR Studio maps to a specific model: text, analysis, transcription, chat, and agent reasoning run on Gemini 2.5 Flash; all nine image workflows run on Nano Banana 2 Flash; video renders on Veo 3.1; narration on Gemini 2.5 Flash TTS; and semantic search on Gemini Embedding 001. Two new Google models are being integrated next: Gemini Omni Flash for conversational video editing, and Nano Banana 2 Lite for high-volume image generation.
In Production Today
- Gemini 2.5 Flash: Text, analysis, transcription, chat, mind maps, and agent reasoning — in 30 languages
- Nano Banana 2 Flash: Every image: 17+ deck styles, 33 infographic types, face-accurate thumbnails, editing
- Veo 3.1: Presenter videos, animated slideshows, and agent video — with a Fast variant for volume
- Gemini 2.5 Flash TTS: Natural narration and voiceover across every video and audio asset
- Gemini Embedding 001: Semantic search and grounded Notebook Chat across your whole library
Integrating Next
- Gemini Omni Flash: Conversational video generation and editing — refine any video by describing the change
- Nano Banana 2 Lite: Google's fastest image model, for bulk thumbnails and batch renders at scale