Recently Google Translate announced the ability to hear translations into English spoken via text-to-speech (TTS).
Looking at the Firebug Net panel for where this TTS data was coming from,
I saw that the speech audio is in MP3 format and is queried via a
simple HTTP GET (REST) request:
http://translate.google.com/translate_tts?tl=en&q=text.
Google Translate notes
that the speech is “only available for short translations to English”, and it turns out
that the TTS web service is restricting the text to 100 characters.
Another restriction is that the service returns 404 Not Found if the request
includes a Referer header (presumably one that is not for translate.google.com).

In spite of the limitations of the web service which certainly reflect
the intention that the web service is only to be used by Google Translate,
thanks to the new HTML5′s Audio element and
rel=”noreferrer”,
the service may be utilized by client-side web applications like following (Google Chrome 4 recommended):

Here is a nice mashup that marries HTML5 Audio support in modern browsers with the new Google Translate API that does text to speech (for them) , also try French Ubiquity command.