1. Unlike a compiled program, which is converted from source code to an executable one time, by a compiler, and then run from its binary form, an interpreted program is converted to binary on the fly each time it is run, by an interpreter program. Interpreted languages (and thus their programs) tend to be slower than compiled and p-code languages/programs, and generally have limited authorization to low-level operating system functions or direct hardware access. On the other hand, they do not require compilers (which can be expensive), are often included along with operating systems, and are usually easier to program than compiled languages. Examples of interpreted languages are BASIC, Perl, Python and REXX/Object REXX. From I-gloss

2. An interpreted language depends on an interpreter program that reads the source code and translates it on the fly into computations and system calls. The source has to be re-interpreted (and the interpreter present) each time the code is executed. Interpreted languages tend to be slower than compiled languages, and often have limited access to the underlying operating system and hardware. On the other hand, they tend to be easier to program. See Compiled language and P-code language. From Linux Guide @FirstLinux