I am new to Bing Speech and have been exploring using it for a proof of concept. The audio streams I need to transcribe will potentially be over 10 minutes in length and want to understand the limitations of this API with these longer streams.
I read in the API docs that the LongDictation mode can be used for an utterance up to 10 minutes long and the overall client library documentation says the API can be used for an audio stream of up to 10 minutes long.
With using the example code provided with the C# service library I tested a 20 minute long audio file and was able to transcribe the entire thing.
When the docs mean utterance is this synonymous with audio stream?
Was this a fluke that I was able to transcribe this entire 20 minute long audio file?
Hi Everyone,
I am new to Bing Speech and have been exploring using it for a proof of concept. The audio streams I need to transcribe will potentially be over 10 minutes in length and want to understand the limitations of this API with these longer streams.
I read in the API docs that the LongDictation mode can be used for an utterance up to 10 minutes long and the overall client library documentation says the API can be used for an audio stream of up to 10 minutes long.
With using the example code provided with the C# service library I tested a 20 minute long audio file and was able to transcribe the entire thing.
When the docs mean utterance is this synonymous with audio stream?
Was this a fluke that I was able to transcribe this entire 20 minute long audio file?
Thanks!