The Replicate connector for Muse

Run any AI model by describing what you want.

The Replicate connector lets Muse run AI models from Replicate’s catalog and poll the results. Image generation, upscaling, transcription, music — thousands of models become callable by plain-language request.

It turns Muse into a model router: describe the outcome, and Muse picks the run, submits it, waits for completion, and brings back the result.

What Muse can do with Replicate

Run models from Replicate’s public catalog
Poll long-running predictions until they complete
Generate images, audio, video, and text with specialist models
Chain model outputs into multi-step creative workflows

Try asking

“Upscale this image 4x and sharpen the details.”
“Transcribe this audio file and give me the key quotes.”
“Generate a lo-fi track I can use as background music.”

Safety notes

Model runs bill to your Replicate account — Muse confirms before expensive runs.
Outputs come from third-party models; review them before publishing.
This is a community-built connector. Review its permissions before connecting.

How to connect Replicate

Open the Muse app, go to settings, and find connectors. Link your Replicate 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 models can Muse use?

Any public model on Replicate that the skill supports. Ask Muse for a model by task, it can suggest well-regarded options for image, audio, or video work.

How long do runs take?

Seconds to minutes depending on the model. Muse polls the prediction and returns when it’s done, so you don’t have to watch it.

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 →