2,349 questions with Azure Speech in Foundry Tools tags
Azure Batch Transcription: Consistent ~12h failure with "InvalidUri" for diarization-enabled jobs
Azure Batch Transcription: Consistent ~12h failure with "InvalidUri" for diarization-enabled jobs Problem I'm using the Azure Speech-to-Text Batch Transcription API with diarization enabled (maxSpeakers: 2, locale: ja-JP). A subset of jobs…
AI answer
Unable to get Azure Speech Service authorization token. REST API always returns 401 for Japan West region.
I am trying to use Azure Speech Service Text-to-Speech through the REST API. My Speech resource was created in the Japan West region. I followed the official documentation and tried to get an authorization token with this endpoint: POST…
Base Model 20250808 Internal Error when training with Structure Text file
When I train a custom model using a structure text file and output file using 20250808 build (english) I get an failure for the model and it says internal error. The structure text and output files are error free when I uploaded them. I was successfully…
Azure AI speech doesnt load at all, ever
I tried hard reset and incognito, nothing works. I am using google chrome. I opened azure account today and struggling since the very begining. Tried to even run it in vs code or make my own small html program just not to have to deal with this thing. I…
How do I download a Speech Studio Voice Gallery voice just for my TTS programs?
I use text to speech programs to help my ADHD brain read long documents, like textbooks from back in college or contracts now that I'm a "real job" adult. The default TTS voices (Mark, David, and Zira) sound robotic and grating, but the…
In azure TTS speech playground, there is no way to generate speech
I'm in the speech playground text to speech area. It feels like there should be a box to enter text but there isn't. There is however, a "try it out" in each voice sample. However, entering text in that area and clicking play produces no sound.…
Azure Speech Service: ConversationTranscriber via Private Endpoint returns 0 segments with 140s session_stopped delay - canadacentral
Service Azure Cognitive Services — Speech Service (azure-cognitiveservices-speech==1.46.0, Python), AKS canadacentral, Private Endpoint. Scenario Using ConversationTranscriber with the universal/v2 real-time endpoint accessed via a Cognitive Services…
How to implement AEC on iOS using 'MicrosoftCognitiveServicesSpeechEmbedded-iOS' (1.49.1)
What is the solution to implement AEC echo cancellation on iOS? The SDK used is 'MicrosoftCognitiveServicesSpeechEmbedded-iOS' (1.49.1) The specific requirement is to always turn on continuous STT, and at the same time, the speaker has TTS sound playing.…
Batch Transcription API – Excessive Processing Time (24+ hours for 2h 24m audio)
We are experiencing an unexpected and significant delay with the Azure Cognitive Services Batch Transcription API. Issue: An audio file of approximately 2 hours and 24 minutes in length has been submitted for batch transcription and remains in a…
AI Foundry Fine-Tuning: 403 Error When Uploading Output Format Training Data with BYOS Enabled
I'm using AI Foundry for fine tuning my custom speech model. I needed content logging and I want that data to be stored in my BYOS (Bring Your Own Storage) storage account, but once I've done that, I'm unable to upload training data of type Output…
Improving the speed of speech recognition processing in Disconnected Azure Speech Containers
I am using a disconnected container for Azure Speech. Please let me know if there is a way to improve the response of the speech-to-text processing. The current system returns the final results 3 seconds after a 5-second speech segment when performing…
Azure OpenAI Realtime client_secrets returns 500 when input_audio_transcription is included (Sweden Central)
We are seeing a consistent server-side failure in Azure OpenAI Realtime when requesting client secrets with input_audio_transcription enabled. Environment Region: Sweden Central Resource: LBBD-OpenAI-Sweden-Dev Subscription:…
AudioEchoCancellation with PersonalVoice is not working on the Voice Live API
AudioEchoCancellation is working without AzureStandardVoice but not with PersonalVoice via the azure.ai.voicelive.models Voice Live python SDK
Crash when app enter background
#37 0 libc++abi.dylib __cxa_get_exception_ptr +88 1 libc++abi.dylib __cxa_throw +92 2 libc++.1.dylib std::__1::__throw_system_error[abi:ne190102] +92 3 libc++.1.dylib std::__1::__throw_system_error(int, char const*)…
zh-CN voices: mstts:express-as styles and paralinguistic tags produce identical output regardless of value
curl --location --request POST "https://${SPEECH_REGION}.tts.speech.microsoft.com/cognitiveservices/v1" \ --header "Ocp-Apim-Subscription-Key: ${SPEECH_KEY}" \ --header 'Content-Type: application/ssml+xml' \ --header…
Cognitive services STT batch transcription: incomplete/cut-off transcripts
Hi, The URLs/sources in this ticket have been replaced with placeholders, but are of course available for support upon request. We are using batch transcription through the endpoint:…
Japanese Voice-to-Text: Preventing Unwanted Kanji Transcription for Names
When using Azure Speech to Text for batch transcription of conversations in Japanese, there is an issue with person names being transcribed into incorrect Kanji characters. A custom speech model has been created to handle specific industry terms, but…
Loading subscriptions
I have set up an account and I am trying to use the Azure speech studio. But when I go there, it just gets stuck on 'Loading subscriptions'. Is it to do with multiple account conflicts or something?
Custom Avatar
I am unable to create custom avatar for my subscription. I had filled the form for the access approval and haven't received any response to it yet
Changing ProfanityFilter Settings in Disconnected Azure Speech Containers
I am using a disconnected container for Azure Speech. docker image ls REPOSITORY TAG IMAGE ID CREATED …