Generating data from an exponential distribution by including correlation between two random variables

Question

Suppose X~exp(.67) , Y~exp(.45) and Z~exp(.8) . X now correlates with Y with a correlation coefficient of -0.6. Again, X correlates with Z with a correlation coefficient of -0.6. How can I include these correlations to generate random variables X , Y and Z ? I know if there was no correlation between them, then I could just generate data X <- rexp(n=10, rate=.67) , Y <- rexp(10, .45) and Z <- rexp(10, .8) .