System, method and program product for transcribing an audio file included in or referenced by a web page. A language of text in the web page is determined. Then, voice recognition software of the language of text is selected and used to transcribe the audio file. If the language of the text is not the language of the audio file, then a related language is determined. Then, voice recognition software of the related language is selected and used to transcribe the audio file. The related language can be related geographically, by common root, as another dialect of the same language, or as another language commonly spoken in the same country as the language of the text. Another system, method and program product is disclosed for transcribing an audio file included in or referenced by a web page. A domain extension or full domain of the web page and an official language of the domain extension or full domain are determined. Then, voice recognition software of the official language is used to attempt to transcribe the audio file. If the official language is not a language of the audio file, then a language related to the official language is determined. Then, voice recognition software of the related language is selected and used to transcribe said audio file. The related language can be related geographically, by common root, as another dialect of the same language, or as another language commonly spoken in the same country as the official language.