The LumenVox ASR includes support for American, Australian/NZ, UK and Indian English, Mexican Spanish, Colombian Spanish, and Canadian French, while the TTS has support for well over a dozen different languages.

By setting the language identifier in a grammar or an SSML document, you can load different ASR acoustic models or TTS voices and effectively work with a variety of languages.

Installing Languages

The LumenVox ASR comes with the American English acoustic model installed, while other languages must be downloaded and installed separately. Installing different languages for the TTS is as simple as installing another voice.

It is very important to note that you cannot have two acoustic models active the same time when performing speech recognition. Within an application, you could switch between English and Spanish, but you could not decode an utterance against both models at the same time. This means you cannot have two grammars with different languages active at once — doing so will cause an error.

Which Language to Use?

If the primary language your application needs to recognize is supported, then you will want to use that language. Applications deployed in the United States would be best served by American English, as opposed to Australian English.

Even if your language is not supported, you may find that one of our acoustic models suits your application. For instance, if you want to recognize Spanish speakers from Spain, our Mexican or Colombian Spanish models may work. Likewise, you may find that Australian English is closer to English spoken around the world than American English.

You may need to experiment a little bit to see which model works best for your speakers. Try different models and add phonetic spellings for words that are commonly misrecognized.

For more information, please see the phonetic spelling help document or contact us at 1–877–977–0707.

Software Type