Speech to text has been one of the most exciting Azure Media Services components since the original release of Azure Media Indexer in 2014.
Today we are ready to release the following new languages to the "Azure Media Indexer 2 Preview" Media Processor: Russian, British English, and Mexican Spanish.
Currently we support the following languages:
- (new) Russian [RuRu]
- (new) British English [EnGb]
- (new) Mexican Spanish [EsMx]
- English [EnUs]
- Spanish [EsEs]
- Chinese (Mandarin, Simplified) [ZhCn]
- French [FrFr]
- German [DeDe]
- Italian [ItIt]
- Portuguese [PtBr]
- Arabic (Egyptian) [ArEg]
- Japanese [JaJp]
In order to run a task against media containing speech in the Russian language, use the following task preset:
{
'Version': '1.0',
'Features': [{
'Options': {
"Language": "RuRu"
}
}]
}
Feel free to swap out the language parameter for any of the supported languages in the list above.
Still not sure what Azure Media Indexer 2 is? Read the introductory blog post to learn how to extract the speech content from your media files.
Want to get started? Check out the official documentation.
To learn more about Azure Media Analytics, check out the introductory blog post.
Have feedback? Share it on our feedback forum.