The invention concerns a method of switching from one original dialog system (1), which communicates with the user using its own dedicated speech recognition and/or speech output unit (6), to a target dialog system (2), which also communicates with the user using its own dedicated speech recognition and/or speech output unit (7), whereby the language of the speech recognition and/or speech output unit (7) of the target dialog system (2) can be set. The original dialog system (1) transfers a language information parameter (P.sub.2) to the target dialog system (2), as a result of which the language which the original dialog system (1) used for communication with the user is specified. The target dialog system (2) uses this language information parameter (P.sub.2) to set the language of the speech recognition and/or speech output unit (7) for further communication with the user.