Our approach to address the question of online video accessibility for people with sensory disabilities is based on video annotations that are rendered as video enrichments during the playing of the video. We present an exploratory work that focuses on video accessibility for blind people with audio enrichments of videos composed of speech synthesis and earcons (audio notifications). Our main results are that earcons can be used together with speech synthesis to enhance understanding of videos; that earcons should be accompanied with explanations; and that a potential side effect of earcons is related to video rhythm perception.