Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,774 questions
use speech to text sdk When using Bluetooth headset
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(35.2, 72%, 13%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EV%3C/text%3E%3C/svg%3E)
voicerec
1
Reputation point
1.During meetings using teams with Bluetooth headset。
2.Open my application, which uses speech to text SDK.
3.What I expect is that the voice I say and the voice I hear can be translated into text。
But the actual effect is that only my voice is translated into text
Can I say and the voice I hear be translated into text with Bluetooth headset using speech to text SDK??
{count} votes
-
romungi-MSFT 46,831 Reputation points Microsoft Employee2021-11-05T10:00:52.077+00:00 @voicerec In both the cases you are using the speech to text option with the SDK. It should be possible to perform both with your app, You might need to ensure the right audio config is setup for both the cases. That is, for your voice you use microphone as input and for the response or audio from other user you use the incoming audio stream.
If this is something you want to achieve with MS teams this is already built-in with teams as live transcription. I hope this helps. -
voicerec 1 Reputation point
2021-11-09T02:36:28.93+00:00 You might need to ensure the right audio config is setup for both the cases.
Can you tell me how to do for audio config?
That is, for your voice you use microphone as input and for the response or audio from other user you use the incoming audio stream.
My voice can already be converted to text using the microphone with STT SDK.
“use the incoming audio stream”
→ What is meaning？ Does it mean the following?
First， convert audio from speaker into audio files using [core audio APIs] , and then convert them into text using the SDK interface [PullAudioInputStream ] or [PushAudioInputStream]？ -
romungi-MSFT 46,831 Reputation points Microsoft Employee
2021-11-10T07:28:19.243+00:00 Yes, that is the scenario I am referring to. If it is realtime meeting then it might not be ideal to get transcription correctly. The azure speech conversation transcription feature can support this but this requires the speech devices SDK.
-
voicerec 1 Reputation point
2021-11-10T08:21:06.197+00:00 My program will be applied in Japan,. Hasn't this feature been opened in Japaneast regions?
<Only available in the following subscription regions: centralus, eastasia, eastus, westeurope>
Sign in to comment
Sign in to answer