Troubleshooting Document Count Issues in Azure Search Indexer
What could cause the document count to not increase while Azure Search indexer remains "In Progress"? PS - Based on common issues that we have seen from customers and other sources, we are posting these questions to help the Azure community.
MS Translator Conversations listener and speaker errors
I first posted in the MS community, and a moderator informed me to post here. Apologies if this is tagged incorrectly. I regularly use Microsoft Translator Conversations in my classroom. I use an iPad or Android phone (both have the most updated apps)…
Azure Batch Transcription Rest API with ENTRA ID and managed identities is not working
I am tried Azure Speech to Text Batch Trancription API with Entra ID. However, Entra ID seems not supported. Can someone help me with an example for rest api with ENTRA ID and managed identities using Python
How to use an Microsoft Entra ID to authenticate with the Speech to text REST API (for batch transcription
I looks like you can only authenticate to the "Speech to text REST API" with a api key (Ocp-Apim-Subscription-Key). What we would like is to authenticate with a Microsoft Entra ID. Why? Our application is running a AKS and all our containers…
Does the Fast Transcription service (part of speech to text) have possible long delays before processing like batch processing does?
Hello Im trying to decide which service i should use to convert speech to text im currently using prerecorded audio clips from a mobile app being sent to the API and then needs to send the text result back as soon as possible. Real-time Transcription is…
When is the GA release for customization of Avatars in Microsoft TTS Avatar service and non-photorealistic options for custom avatars
Two part question on the TTS Avatars When is the TTS Avatar - customization of Avatars going to be GA ? How can we do non-photorealistic Avatars (i.e, Animated/Cartoon characters like the Microsoft Mesh)?
Azure Cognitive Speech TTS : Is the free tier included in standard
I would like to get a clarification about Azure Cognitive Speech TTS cost calculation. There is different for >Tier TTS usage : Free, Pay as you Go, Commitment. I would like to know if you are using the Commitment - standard tier, do you get the free…
Speech-to-text: Disfluency Removal configuration
I am using the speech-to-text REST API (python) to do some research regarding fillers, pauses, and backtracking in Japanese (ja-JP). Can I config disfluency removal while using the Speech-to-text service? I need to have true text with all the fillers…
Spanish and English text in the same Microsoft TTS
How can I make the Microsoft TTS pronounce words in Spanish and English in the same pronunciation if the default language is Spanish?
does TranslationRecognizer use "Speech to Text" or "Speech Translation" as per the pricing on the website.
Hello, Im using both TranslationRecognizer and SpeechRecognizer classes from the azure Microsoft.CognitiveServices.Speech sdk but unsure what costing bracket they fall under. there are prices for "Speech to Text" or "Speech…
Multilingual voice information in dotnet SDK
I installed the latest version of the speech sdk <PackageReference Include="Microsoft.CognitiveServices.Speech" Version="1.40.0" /> When pulling the voices using the sdk, var voices = await synthesizer.GetVoicesAsync(); i do not…
Azure subscription was disabled?
Anybody know why I hit below issue when I tried to use Speech Service? {"error":{"code":"ReadOnlyDisabledSubscription","message":"The subscription 'e6a24fa0-37aa-48eb-99f2-xxxxxxxxxx' is disabled and therefore…
How to get the "timed script file" (sentence boundary) when using batch synthesis for avatar text-to-speech?
I've tried to enable word or sentence bounday to get the "time-stamped script" when generating an avatar text-to-speech video. Everything is running fine but the only outputs im getting are the video and the standard summary.json file #…
Intonation does not work correctly
Hi, I tried to change the stressed word in the sentence using all the examples available. The voice is Emma, and Emma is multilingual (EN-US). When adding prosody in SSML or just pitch or intonation, nothing happens. Now I try to add just weird…
Azure AI Speech Studio
What is the difference between Personal Voice and Custom Neural Voice Lite in Azure Speech? I am looking for a clear distinction to help me choose one over the other. Additionally, after creating a new Personal Voice in Azure Speech Studio, how can I…
Has Diarization in Speech SDK been implemented for overlapping audio of multiple speakers speaking simultaneously ?
To the Microsoft Support Team, We have been using ConversationTranscriber of the Azure Speech SDK, to implement Diarization in our project, and have encountered an issue in which we need your assistance. In our project, the Transcriber works well…
My Speech Congnitive Basic Model can not finish training
I want to training a congnitive model to help me do speech key words cognition. I choose basic model but it have run for over 10 hours still not get any result. The doc says it only takes few minutes. Now the model still inprocessing without any result.
looking for python code examples for fast transcription api
can you please share some python code examples for fast transcription api ? I can't find much...
How to send a byte array to Azure Speech Service (Speech to Text)
We would like to use Azure Speech Service (Speech to Text) for our project. I have tried all the examples on this page: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-recognize-speech?pivots=programming-language-csharp I…
Basic SSML doesn't import correctly
I used the example on this page: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-audio-content-creation It does not import correctly, it seems like it adds extra lines before and after when viewed in the UI.