No module (_speech_py_impl) found error in python azure functions, could not install
No module (_speech_py_impl) found error in python azure functions, could not install 1 Logged in using ssh, navigated to /home/site/wwwroot/functionname - Installed modules but the same error 2 Logged in using bash, navigated to /home/site/wwwroot/ -…
Speech to Text Rest API to accept authorization token for RecordingsUrl
Hi, my company has been using Azure's speech to text service and are happy with the results. However, we've hit a snag. For the RecordingsUrl parameter, I understand we will be passing in a blob uri that's public facing (no auth required), but our…
Text to Speech does not work using Local CMD/Powershell
Hello, I am trying to convert text to speech through Azure's Speech Service, using my local PC's CLI. After i sucessffully logged in through the relevant CMDLET (Connect-AzAccount), i hit the following commands: .\spx synthesize --nodefaults --region…
What servers allow Long Audio API for text-to-speech with Aria vocaloid on Azure?
What servers allow Long Audio API for text-to-speech with Aria vocaloid on Azure?
Why can't I resolve SPXSpeechConfiguration.framework when I do 'pod install' with the Podfile from helloworld from MSFT Cognitive Services SDK for Swift for TTS?
For more information: https://video2.skills-academy.com/en-us/objectivec/cognitive-services/speech/spxspeechconfiguration I cannot find the SPXSpeechConfiguration when I use IntelliSense for Xcode. What is missing?
Custom voice in DUTCH
Hello I am trying to use speech in order to create a custom voice but in the Dutch language. Is it possible to create a custom voice in DUTCH?
Using text to speech for video narration (using speech studio)
I hope someone can help. I create local public sector health videos and would like to use the text to speech mp3 downloads to narrate videos. (They are ideal). I'm seeking clarification on whether this is permitted / allowed? I only intend using the…
Data stored by Azure Speech
Hi I use Azure Speech for speech-to-text and text-to-speech, and I would like to know more about data storage when using this service. Which of the following elements are stored on Microsoft servers ? Audio : user's voice when using…
Do you have any examples with Long Audio API using Objective-C or Swift 5+?
Do you have any examples with Long Audio API using Objective-C or Swift 5+?
Custom Speech quality issue.
I am developing a speech to text solution using Azure Custom Speech API as a backend. I noticed the drop in the quality of custom trained models. Previously, I was kind of impressed by the result of a custom trained model where I can train with Text…
Can't send API Requests from python code hosted on AWS Lightsail instance
I have a django website that is hosted on an AWS Lightsail. I am trying to add in a Speech to text tool in it. I have tried Microsoft Azure Speech to text APIs for this purpose and have used sample code from the website. The code works fine when i'm…
How do I calculate the cost of creating a custom voice on Cognitive Services/Speech Service?
I have signed up for Speech Service and I have the data for training a model to create a custom voice by cloning the existing transcribed utterances. However, before I kick off the training of the model, I need to understand how much it will cost me.
Dutch Speaker Recognition
Hi, I have been doing some research on the Speech-to-Text API in Microsoft Cognitive Services. We want to develop a Speech-to-Text application in Dutch which would also have the ability to recognize multiple speakers. I found out that on…
using start_keyword_recognition for keyword detection
I am following the below documents for keyword detection - azure.cognitiveservices.speech.recognizer custom-keyword-basics I have followed each step. Created the keyword model. However I am stuck at using the recognizer class and…
Cannot delete Custom Speech model due to transcription reference
Am attempting to delete a Cognitive Service Custom Speech Model. However the following error comes up The model is referenced by a transcription. Please delete all transcriptions conducted with this model first. I have had this issue on a model from a…
MP3 Content Type for Creating a MediaSource
I am using Azure SSML TTS to get a C# Stream object in "audio-16khz-64kbitrate-mono-mp3" format and other customizations. I subsequently create a byte[] stream from it for cross-platform Xamarin distribution. For UWP I convert it to a…
speech to text sdk
is there golang sdk for speech to text? and the protocol is grpc
How to use en-SG in Speech to Text API V3.0 and Customize model
en-SG list in supported language, and support customize Language model. (at https://video2.skills-academy.com/en-us/azure/cognitive-services/speech-service/language-support) I want to use RESI API v3.0 speech to text for English (Singapore), and…
azure speech recognition crash the console-app on linux IOT
hi there, i have a console app that uses azure for speech recognition offline from microphone (by KeywordRecognitionModel table) on linux IOT(raspberry pi). when i run it, at first time it works correctly and can recognize my word, but after 3 or more…
Cognitive Speech Services Cloud in production - exporting voice waveform recordings
We are looking to put Azure Speech Services Cloud (transcription) in production, but want the ability to export any voice recordings (waveforms) that are submitted to the cloud service by our customers. Is this possible? Thanks, John