The Gemini connector for Muse

Google’s media generation, from inside Muse.

The Gemini connector brings Google’s media generation into Muse: images, video, and text-to-speech, plus model listing. When you want Google’s models in the mix (a different image style, a video clip, a voice read), Muse can reach for them directly.

It is the cross-lab play: Muse orchestrates, Gemini generates, and you compare results against other model providers in one place.

What Muse can do with Gemini

Generate images with Google’s image models
Generate video clips from prompts
Generate text-to-speech audio
List available Gemini models

Try asking

“Generate a product photo with Gemini — a smartwatch on a white background.”
“Create a short video of ocean waves at sunset.”
“Generate a voiceover for this script with Gemini TTS.”

Safety notes

Generated media may carry per-use costs — Muse confirms before running jobs.
Review outputs before publishing; AI media can include artifacts.
This is a community-built connector. Review its permissions before connecting.

How to connect Gemini

Open the Muse app, go to settings, and find connectors. Link your Gemini account with the standard sign-in — Muse never sees your password. Once linked, the connector is available across your conversations. You can scope it to read-only or disconnect it entirely at any time from the same screen.

Questions

Which Gemini models are available?

Muse can list the models your account can access, including image, video, and TTS options.

Why use Gemini through Muse instead of directly?

You get Muse’s orchestration: prompt refinement, comparison across providers, and the result dropped straight into your workflow.

Related connectors

Connector status last checked October 13, 2026. The authoritative, current list lives in the Muse app's settings, under connectors. Back to the full directory →