Azure Cognitive Services - Speech to Text failing to return any transcribed text even with valid audio files
I am working in the automation of IVR systems. I am using speech helper components from Azure Cognitive Services. For the past one month, I am facing latency issues with speech to text. At sometimes, I see S2T returning no text even with valid audio…

Why the Azure Speech Service keeps recognizing English words even though I've set the language strictly to Arabic (ar-AE) in my configuration?”
Hello, I’m using the Azure Speech Service to transcribe audio entirely in Arabic, with the following setup: Region: SwedenCentral Language: ar-AE Audio Source: Microphone Azure Speech SDK: 1.42.0 Key details: The recognition language is set…
Azure Text to Speech Error: Unable to contact server. StatusCode: 1006,
Dear all,We use azure text to speech to synthesise speech. However, recently we keep seeing this error when using Azure Text to Speech service in our application: Error details: Unable to contact server. StatusCode: 1006,…

No response for applying Azure AI Custom Text to Speech Avatar services
I am writing to express my frustration regarding the prolonged status of my application for the Azure AI Custom Text-to-Speech Avatar service. I submitted my application some time ago and have provided all necessary supporting documents to…
What is the Android targetSDK for Java Azure Cognitive Speech SDK?
I am considering using the Azure Cognitive Speech SDK (Java language) in an Android application. I was looking at documentation online, but cannot find the Android targetSDK that the Java library targets when used in Android. I would like to know what…
Why does ConversationTranscriber lose connection to server after about 20 min?
We are doing a live transcription speech to text using the ConversationTranscriber. After calling startTranscribingAsync it runs for about 20 min before a canceled event is received with an error saying "Unable to contact server. StatusCode: 0,…
Use Azure AI Speech service to make real-time transcription with diarized speakers
I adapted a version of the Azure microphone real-time transcription from the the github repo: https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/js/browser/index.html However, when I tried tweaking it to diarize, as…

Azure TTS: Getting non speech audio bytes at beginning and ending of TTS speech
We use Azure's Rest API with the TTS service to generate audio for one of our products. From our logs, it seems starting on February 28, 2025, we started getting audio back with non-speech bytes (two audio blips) at the beginning and end of the audio…
How to enable Text-to-Speech (TTS) for Speech Services
I have an active Azure Speech Services resource under the Standard (S0) tier in the East US region. My API Key works for listing available voices (voices/list), but any Text-to-Speech (TTS) request returns a "404 Resource Not Found"…

Reuse SpeechRecognizer and stream for multiple audio streams?
Hi team, is there any best practice on how to reuse the SpeechRecognizer for stream recognizing user audios? In our application, we know where user start talking and end talking so we can signal speech recognizer for it. The reason I wanted to reuse…
[ISSUE] Pronunciation Assessment in Polish Fails
Hello, the Azure Team, I have noticed audio passed to the Azure Pronunciation Assessment in Polish doesn't work at all. Uploaded audio and even the live microphone in your Azure Speech dashboard fail in Polish. I haven't tested all the languages but the…
Internal error while fine tuning Whisper
While trying to fine tuning Whisper Large V2 I get an internal error: "Model training failedAn internal server error has occurred. Retry after a while. If the issue persists". I've tried several times and different region but the problem…

Is there a mapping between SessionId and LogId
Hi team, I would like to know if there is a mapping between sessionId that Azure SDK provides to the logId with which the transcripts and recordings are logged on Azure. I am referring to this [blog] to log transcripts with Azure. While I can retrieve…
Error when returning audio stream from server using speech synthesis
I was able to generate and produce audio speech on my local server. The API was generating a wav file and storing it in my local file system. The speech was played by an HTML audio tag picking up the local file. When I deployed to the Azure web…
Azure Pronunciation Assessment API – Inconsistent Scores Between Python and TypeScript
Hi Azure Team, We are experiencing a significant discrepancy in pronunciation assessment scores when using the Azure Speech Pronunciation Assessment API with the Python SDK versus the TypeScript SDK. The same audio file and reference text produce good…

Exception [SPXERR_RUNTIME_ERROR 0x1b] When Using SpeechRecognizer with AudioProcessingOptions for Echo Cancellation
I am trying to implement Acoustic Echo Cancellation (AEC) using Microsoft's Speech SDK in C#. I am using AudioProcessingOptions.Create(AudioProcessingConstants.AUDIO_INPUT_PROCESSING_ENABLE_DEFAULT) to enable audio processing. However, I am encountering…
Azure Text-to Speech Error Code: 0x38 (SPXERR_AUDIO_SYS_LIBRARY_NOT_FOUND) when using Python 3.10 on Wep App Service
I followed these 2 guides and everything works fine on my local windows 10 machine using python 3.10., but when I deploy my code using VS Code to my linux basic web app service, running python 3.10, I receive the following…
zh-CN-XiaochenMultilingualNeural voice request timeout
Hey, When using voice zh-CN-XiaochenMultilingualNeural request is timed out. Other chinese voices, for example, zh-CN-XiaoxiaoMultilingualNeural or zh-CN-XiaoqiuNeural works perfectly. Where is the problem?
Introducing interpretation in Microsoft Teams using Azure AI Speech. But when and how?
Hello, I saw a few weeks ago the following Microsoft Azure Video where a call was translated in realtime. https://www.youtube.com/watch?v=r8gzes7aA7s Will be good to test this and be part of the BETA Testgroups. Where can I find more information about…
Azure TTS Speaker Separation Problem
Hello, I followed the instructions at https://learn.microsoft.com/ko-kr/azure/ai-services/speech-service/get-started-stt-diarization?tabs=windows&pivots=programming-language-csharp, but I'm encountering an error. For reference, the subscription key…