The invention describes a system (1) for generating audio-visual summaries for audio-visual program content (3). The system comprises a search unit (4) for locating a pre-generated text summary (5;) associated with the program content (3); a speech synthesizer (6) for converting the text summary (5,) into speech (7); a video 5 summary generator (8) for generating a video summary (9) of the audio-visual program content (3), and an audio/video mixer (10) for mixing the synthesized speech (7) with the video summary (9). Moreover the invention describes an appropriate method for generating audio-visual summaries (5i) for audio-visual program content (3).