Techniques and apparatus for selecting audio content for a content entity in audio-visual content are described. An example technique involves identifying at least one content entity associated with a content item that is accessible to one or more users in a first language over a communication network. One or more attributes of the at least one content entity are determined. A plurality of audio content samples in a second language are obtained. Each audio content sample includes a different audio sample of a portion of speech of the content entity in the second language. A first audio content sample that satisfies a predetermined condition is determined, based on the plurality of audio content samples and the one or more attributes of the at least one content entity. An indication of the first audio content sample is provided.