Feedback - Feature Requests

Add Meta's Llama 4. It has been out for a more than a month. Also deprecate Llama 2 since it is no longer supported.

Request you to consider including if feasible Genspark AI..

I would like to see a feature where a still photo of a person could be uploaded and in return a gif would be formed with eye movement, minor facial musculature, mouth movement and minor body movement, thereby animating the photo.

Would love to use this in the app.

your competitors have enabled a "pause" feature in the text to speech model. Several of the services used by 1min.AI have an ability to add a pause into their text to speech models. This feature allows more direct control when the model does not speak naturally. I am requesting that you add an ability to insert a pause in the text to speech tool.

the 50MB file size is too small. All other sites allow much larger file sizes, especially for audio files.

For the moment the API documentation is really simple and it lacks features. Credit used/left field for streamable content request type model list route to get all models code examples ... if you have any ideas how to improve the API. At this point I was not able to make it work even though my code looks correct (and it's not the first API I use)

Please add the ability to search the web to chat with image.

If we could add 1mn.AI to n8n workflows as an LLM for Agents and choose from the ones you provide, I can tell you, you would bury competition and I would be you herald to promote you guys. Basically facilitating automation by using your API would go a long way.

A text tool that will rewrite content to be more human, not detect that the content is AI or not.