Modern Web search engines still have many limitations: search terms are not disambiguated, search terms in one query can't be in dierent languages, the retrieved media items have to be in the same language as the search terms and search results are not integrated across a live stream of dierent media channels, including TV, online news and social media. The system described in this paper enables all of this by combining a media stream processing architecture with cross-lingual and cross-modal semantic annotation, search and recommendation. All those components were developed in the xLiMe project.