About speaker separation in "fast-transcription-api"

y.ashibe 45

Dear Azure Support Team

https://zcusa.951200.xyz/en-us/rest/api/speechtotext/transcriptions/transcribe?view=rest-speechtotext-2024-05-15-preview&tabs=HTTP

The details of the TranscribeDefinition class are not described anywhere, so how should I do diarization?

{"locales": ["ja-JP"], "channels": [0,1], "diarization": true}
→🆖

{"locales": ["ja-JP"], "channels": [0,1], "diarizationEnabled": true}
→🆖

navba-MSFT 27,065 Reputation points Microsoft Employee

2024-07-29T05:31:52.0633333+00:00
@y.ashibe Welcome to Microsoft Q&A Forum, Thank you for posting your query here!

.

The details to Use the fast transcription API with the relevant header details are explained here: https://zcusa.951200.xyz/en-us/azure/ai-services/speech-service/fast-transcription-create#use-the-fast-transcription-api

.

Request Headers:

curl --location 'https://YourServiceRegion.api.cognitive.microsoft.com/speechtotext/transcriptions:transcribe?api-version=2024-05-15-preview' \ --header 'Content-Type: multipart/form-data' \ --header 'Accept: application/json' \ --header 'Ocp-Apim-Subscription-Key: YourSubscriptionKey' \ --form 'audio=@"YourAudioFile"' \ --form 'definition="{ \"locales\":[\"ja-JP\"], \"channels\": [0,1], \"diarizationEnabled\": true}"'

Hope this helps. If you have any follow-up questions, please let me know. I would be happy to help.
y.ashibe 45 Reputation points

2024-07-29T08:16:40.8633333+00:00

@navba-MSFT

Thank you for answering.

"diarizationEnabled": true

Unfortunately, I couldn't do "Diarization".

https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/

Even if you look at the price plan, there is no price for "Fast Transcription" in the "Diarization" item, so it doesn't support it, right?
navba-MSFT 27,065 Reputation points Microsoft Employee

2024-07-30T03:32:20.77+00:00

@y.ashibe Thanks for your reply. I w am looking into this. I will get back once I have an update on this.
y.ashibe 45 Reputation points

2024-07-30T04:37:39.68+00:00

@navba-MSFT

Thank you, I appreciate it.

Accepted answer

navba-MSFT 27,065 Reputation points Microsoft Employee

2024-07-31T09:37:12.14+00:00

@y.ashibe Apologies for the late reply. I appreciate your patience on this.

.

I got a confirmation from the Product Owners that the diarization is not yet supported with Fast Transcription API. We are working on it and plan to support around mid/late September.

.

Hope this helps.

**

Please do not forget to "Accept the answer” and “up-vote” wherever the information provided helps you, this can be beneficial to other community members.
Please sign in to rate this answer.

1 person found this answer helpful.
Schuster, Björn 0 Reputation points

2024-12-18T09:08:29.2066667+00:00

Sorry for hijacking this Thread, i am facing the same problem, tried diarizationEnabled=true as well as diarization={"enabled":true}

Can you confim that it should work by now or is it still not fully supported?
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.

Share via

About speaker separation in "fast-transcription-api"

0 additional answers

Your answer