What is expected date to have AUDIO_INPUT_PROCESSING_ENABLE_V2 feature on Linux systems?
I'm having some issues with the current echo cancellation algorithm on Linux system, and I've noticed that there is enhanced version. Is there any date specified when this feature will be available on Linux systems? …
How to solve Login Problem to Speech Studio
Hello, trying to login on speech.microsoft.com I have now this Error Message. How can I solve that? Some Days ago it worked perfectly... AADSTS500200: User account 'XXXXXX' is a personal Microsoft account. Personal Microsoft accounts are not supported…
Speechsynthesizer causes JVM crash during finalization (Speech client-sdk for Java)
https://github.com/Azure-Samples/cognitive-services-speech-sdk/issues/2701 As I detailed in the above github issue, there is a reproducible bug in the Java client-sdk for Azure Speech. During Finalization of Speechsynthesizer Instance it can cause a…
Support of Special Character "&" in Azure Text-to-Speech Service
I've noticed that the TTS service does not pronounce the "&" character, which is quite common in various contexts such as company names, product titles, and more. This limitation affects the whole output, so in case I have 3 sentences to…
exception.cpp:125 About to throw Exception with an error code: 0x25 (SPXERR_UNEXPECTED_TTS_ENGINE_SITE_FAILURE)
java.lang.RuntimeException: Exception with an error code: 0x25 (SPXERR_UNEXPECTED_TTS_ENGINE_SITE_FAILURE) at com.microsoft.cognitiveservices.speech.util.Contracts.throwIfFail(Unknown Source) at…
PronunciationAssessment does not include ContentAssessmentResult for Unscripted Assessment Results
I am attempting to try out the pronunciation assessment and will really use the TopicScore and GrammarScore from the content assessment result. I am using a modified version of the sample python code given in your github:…
Azure AI Fast Transcription confidentiality policy
Could you provide information on how the Azure AI fast transcription API ensures the confidentiality and security of audio data and transcriptions in comparison to the real-time and batch transcription service? I can see the real-time speech to text…
When I try TTS ervice I got:WebSocket upgrade failed: Authentication error (401). Please check subscription information and region name
When I try TTS ervice I got:WebSocket upgrade failed: Authentication error (401). Please check subscription information and region name. I shure I use correct subscription Key and eastus region (Really I live in other region).
Why has the batch synthesis tts word.json output changed when using <break /> tags in ssml?
A month ago I was using the batch synthesis tts api and was receiving correct responses for the word.json file. Today I seem to be receiving different responses for the word.json I haven't changed my code at all. The audio output is correct. Here's my…
Issues with Processing Encrypted WAV Files Using Fast Transcription API
I have successfully used the Whisper model to transcribe a batch of 50 encrypted WAV files without manually inputting the file paths. However, I'm encountering difficulties when attempting to perform the same task with the Fast Transcription API. Could…
Is it possible to get subtitles or a timed script with batch synthesis text to speech avatar?
Using batch text-to-speach or batch avatar API, is it possible to get subtitles on the generated video? Or even better, getting a script of the text with time stamps. I was hoping to do some front end shenanigans by creating texts highlights, as the…
Possible errors during batch speech to text?
Hi, im using azure speech to text batch api, what are the possible error messages that could come in the transcription report for the failed transcriptions, not for the failed batches, for the failed transcriptions. If i send 1000 files for transcription…
Could not initialize class com.microsoft.cognitiveservices.speech.SpeechConfig on contos7
在本机win10 上 运行是 正常的 但是 软件打war包 后 到服务器上centos运行报错 Could not initialize class com.microsoft.cognitiveservices.speech.SpeechConfig 看了很多说明,尝试各种方式步骤 还是不行。 有没有详细点的检查教程啊? 研究了快一个月了。崩溃。。。。。
Cannot Connect Locally to when using Microsoft.CognitiveServices.Speech
Hello Everyone, I am trying to build a method that detects the language of the audio I provide it. My application translates audio but since we batch transcribe and also use a custom model, I cannot use languageIdentification. Therefore, I am trying to…
confidence is always 0
In the SPXSpeechServiceResponseJsonResult returned by addRecognizingEventHandler, confidence is always 0
error message "Resource was disallowed by policy. (Code: RequestDisallowedByPolicy)"
I initialized "Azure AI Speech" but got an error. Can someone help me?
stt AudioConfig.fromWavFileInput The program is not running anymore
log.info("azureAsrService sn={} filepath={}",sn,filepath); AudioConfig audioConfig = AudioConfig.fromWavFileInput(filepath); log.info("init audioConfig"); SpeechRecognizer recognizer = new SpeechRecognizer(getSpeechConfig(sn),…
How to integrate Azure AI Studio Chatbot with Shopify
So I would like to know if there is any javascript embedding that we can paste after we have created our custom chatbot in Azure AI Studio, to integrate with my website on shopify
Does Custom Neural Voice support Viseme output?
I could not find any documentation on the SSML supported by custom neural voice. I would like to know if Viseme events are supported.
Does Real Time Azure Speech To Text support providing display form word level timestamps
I have observed that the Batch STT mechanism in Azure Speech Studio allows me to retrieve either / or "Display form word level timestamps" and "Lexical form word level timestamps". This is a great choice, depending on my use case. I…