This paper presents a speech interface to extract domain-specific information from a tourism semantic website as a way to avoid complicated and unfriendly SPARQL queries. First, we present a user-oriented website with a semantic knowledge model of tourism. This model is also known as ontology, represents a common understanding of domain in which semantics of data is machine understandable. Second, we make in Raspberry Pi an interface which has the capability to recognize speech queries and give an oral response. Our interface analyzes each speech query, convert speech to text and extract keywords from the text. Later, these keywords are compared with a list of pattern templates to match an SPARQL query. Finally, this SPARQL query extracts information, in text, from the ontology of the semantic website; and the interface will read it, in voice, for the user. Google Cloud Speech API makes speech-to-text conversions and Text-to-Speech conversions with SVOX Pico. As results, we will present the response time of different speech queries, where we show three stages; time of our website server, the response time of Google Cloud Platform and a constant latency time. With this interface, we reduce barriers of access to the semantic web for people without technical knowledge of Semantic Web technologies and visually impaired people.