Limit sample size in silhouette function

Does anyone have an idea of how can I limit the number of samples taken into account by silhouette function?:

[s,h] = silhouette(X,clust)

I have large sample size and my computer is calculating for a too long time... I know taht this is possible for example in python:

sil = metrics.silhouette_score(data, cluster-labels, metric='euclidean', sample_size=300)

I dont want to select a number of cases by myself because I suppose that this should by by chance...

Thank you in advance!

Maria.