Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,657 questions
0 answers
Speech-to-text initialization hanging
Hi, I'm using speech-to-text services C++ SDK for Linux. I've build a test app following the guidelines from here: …
asked 2021-09-16T09:03:20.693+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(246.4, 65%, 33%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EIH%3C/text%3E%3C/svg%3E)
Ivan H
1
Reputation point
commented 2021-09-21T10:56:04.177+00:00
romungi-MSFT
44,581
Reputation points Microsoft Employee
0 answers
Custom Neural Voice & Viseme Event - Question
Hello I am a user of Custom Neural Voice. However, I have a few questions while using it. Viseme Event doesn't seem to come out in Custom Neural Voice. Is this correct? Is there any way to get a Viseme Event from Custom Neural Voice? If there…
asked 2021-09-16T06:22:56.963+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(137.6, 90%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EA%3C/text%3E%3C/svg%3E)
현우 오
181
Reputation points
commented 2021-09-17T10:09:26.93+00:00
romungi-MSFT
44,581
Reputation points Microsoft Employee
0 answers
functionality in speech to text API
In Azure Cognitive Service, and in Speech to Text API, there is only one Functionality Automatic Punctuation. Dictation, and text normalization is not includes here
asked 2020-12-23T18:14:43.733+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(144, 94%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESC%3C/text%3E%3C/svg%3E)
Sanniddha Chakrabarti
36
Reputation points
commented 2021-09-15T11:56:12.307+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(169.60000000000002, 88%, 26%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EFT%3C/text%3E%3C/svg%3E)
FIXED-TERM Alzubi Abdulmalik (DC-AE/ESW2)
1
Reputation point
1 answer
Speech language detection for speech-to-text
Hi, We want to use your solution for speech to text service. Our use case is the following one, we want to get the transcript from an audio, but we do not know from which language the audio is. I noted that the language detection has some limits: …
asked 2021-09-01T16:04:22.73+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(275.2, 61%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ELF%3C/text%3E%3C/svg%3E)
laure.florent
1
Reputation point
answered 2021-09-13T23:52:03.083+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(278.4, 1%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EYM%3C/text%3E%3C/svg%3E)
YutongTie-MSFT
50,716
Reputation points
1 answer
Neural TTS languages extension
Hello, I know that in Azure TTS there already exists a multilingual voice JennyMultilingualNeural that can speak 14 languages. Do you know if there is any plan of adding other languages? Especially, if there is a plan to add Czech, Slovak and Polish…
asked 2021-08-23T11:01:22.627+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(195.2, 67%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EFL%3C/text%3E%3C/svg%3E)
Filip Lorenc
1
Reputation point
commented 2021-09-10T05:10:06.383+00:00
Filip Lorenc
1
Reputation point
1 answer
One of the answers was accepted by the question author.
Azure Speech To Text Java Client SDK problem
Hello, I have problems running samples from client-sdk (https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/quickstart/java/jre, …
asked 2021-09-08T09:07:45.603+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(60.8, 76%, 15%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ETM%3C/text%3E%3C/svg%3E)
Tomasz Markiewicz
21
Reputation points
accepted 2021-09-09T11:26:58.013+00:00
Tomasz Markiewicz
21
Reputation points
1 answer
Speech to text for number's in German
Good afternoon everyone, I have a problem with speech recognition and that is with the numbers. I used the speech recognition in German. Sometimes the numbers are converted into words instead of digits. My code is in C #. Could someone help me with this?…
asked 2021-09-08T12:09:46.91+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(233.6, 51%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAA%3C/text%3E%3C/svg%3E)
Abdulmalik Alzubi
11
Reputation points
answered 2021-09-09T02:22:34.43+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(214.4, 45%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EGM%3C/text%3E%3C/svg%3E)
GiftA-MSFT
11,166
Reputation points
2 answers
Custom grammars supported by Microsoft Azure's Speech to Text recognition service?
Hi, I have below 2 queries: Does the speech recognition service support the custom GRXML based grammar for recognition? Does the speech recognition service support the compiled(binary-format) grammar for recognition? We have…
asked 2021-09-07T10:23:18.38+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(48, 38%, 14%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAB%3C/text%3E%3C/svg%3E)
Aman Bhardwaj
1
Reputation point
answered 2021-09-08T11:13:14.59+00:00
Aman Bhardwaj
1
Reputation point
4 answers
One of the answers was accepted by the question author.
Microsoft speech to text doesn't recognize decimal numbers correctly
We're using MS custom speech for german language in our application. When the user says the decimal number "1653,57" (in german: "Eintausendsechshundertdreiundfünfzig Komma fünf sieben") the MS speech service recognizes "1600…
asked 2021-08-31T09:04:42.017+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(211.20000000000002, 72%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAL%3C/text%3E%3C/svg%3E)
Andreas Lange
41
Reputation points
answered 2021-09-07T15:35:10.497+00:00
YutongTie-MSFT
50,716
Reputation points
1 answer
Asking about Speech to text Pronunciation Assessment(About Phoneme Recognition)
Hello, I'm looking for feature that gives me exact result of recognized phoneme. I was able to find that azure speech to text pronunciation assessment supports score for each phoneme of reference text. But I'm wondering if there is a way to get…
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(182.40000000000003, 21%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EM%3C/text%3E%3C/svg%3E)
2 answers
20 second Video limit for Pronunciation Assessment
Hello, Today, we tried to analyze Video speech using the "Pronunciation Assessment". But, at one time, we were allowed to analyze only 20 seconds' videos. How we can analyze the entire video (about 3 minutes)?
asked 2021-07-18T12:26:25.97+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(92.8, 54%, 18%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJK%3C/text%3E%3C/svg%3E)
Junbum Kwon
1
Reputation point
answered 2021-09-07T05:56:29.89+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(3.2, 86%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EYW%3C/text%3E%3C/svg%3E)
Yinhe Wei
1
Reputation point Microsoft Employee
3 answers
I want to use Azure Custom text to speech, is it available in the free plan even after 12 months ?
I want to use the custom text to speech feature of Azure for a personal project of mine. I was wondering if that feature is only available in the 12 months period of a free account or is it forever available. Thanks in Advance.
asked 2021-09-02T01:23:03.713+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(134.4, 8%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJJ%3C/text%3E%3C/svg%3E)
Jagath Jijo
1
Reputation point
answered 2021-09-06T13:41:28.197+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(150.4, 30%, 24%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EYL%3C/text%3E%3C/svg%3E)
Yueying Liu
1
Reputation point
2 answers
Audio library export not working
Hi, I can´t download the audio files from my audio library, the problem is been in the last 3 days. I´ve try to download them as a ZIP file, but not working either. How can I fix it? Jose
asked 2021-04-21T20:35:47.177+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(268.8, 75%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJM%3C/text%3E%3C/svg%3E)
Jose Marquez
6
Reputation points
answered 2021-09-06T09:17:46.18+00:00
Yueying Liu
1
Reputation point
2 answers
Azure Text-to-Speech, Lists in 'Export task' are missing.
I made some TTS script files in Speech Studio and exported them. Usually, I can check them in 'Export task' menu, but lists that I have exported for several days are gone. I tried to export more files and still there's nothing in 'Export task'. …
asked 2021-07-02T00:50:22.32+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(236.8, 84%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ES%3C/text%3E%3C/svg%3E)
Sparta
1
Reputation point
answered 2021-09-06T09:15:30.087+00:00
Yueying Liu
1
Reputation point
2 answers
One of the answers was accepted by the question author.
asked 2021-08-31T11:58:24.463+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(236.8, 85%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKM%3C/text%3E%3C/svg%3E)
Kawsar Mahmud
26
Reputation points
commented 2021-09-04T08:52:46.087+00:00
Kawsar Mahmud
26
Reputation points
1 answer
Error Speech studio
Hello, my name is Jose and I have a problem with the Azure Speech Studio application. When I try to export the text to audio files I get the following message: Error: Only a maximum of 0 paragraphs per export task are supported. Currently, there are a…
asked 2021-08-31T10:20:01.227+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(32, 31%, 13%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EN%3C/text%3E%3C/svg%3E)
Nacho
1
Reputation point
commented 2021-09-03T11:16:20.907+00:00
romungi-MSFT
44,581
Reputation points Microsoft Employee
2 answers
How can I change Azure voices speed with SDK?
We're using Azure voices within an Android App and would like to change the speed (prosody rate) of determined voices. We've found the following link:…
asked 2021-05-13T09:06:50.287+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(288, 13%, 37%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMA%3C/text%3E%3C/svg%3E)
Manuel Aicart
1
Reputation point
answered 2021-09-03T06:35:57.62+00:00
Yueying Liu
1
Reputation point
3 answers
why isn't there an option to store words in Microsoft Azure's Pronunciation Alias window?
We need the ability to save and store words that require special Pronunciation in the Pronunciation Alias window. It's very tedious and time consuming to have to find every instance of word that needs special pronunciation. Please have a look at…
asked 2021-06-14T14:42:53.353+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(83.2, 82%, 18%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EN%3C/text%3E%3C/svg%3E)
ninose
1
Reputation point
answered 2021-09-03T06:18:23.223+00:00
Yueying Liu
1
Reputation point
0 answers
Getting exception when deploy Speech SDK on Azure webapp SPXERR_MIC_NOT_AVAILABLE
Describe the bug When I am trying to deplpy my Speech SDK (from Microphone To Speech)on Azure webapp getting SPXERR_MIC_NOT_AVAILABLE though it is working locally and over local iis deployed also. To Reproduce Steps to reproduce the behavior:…
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(124.80000000000001, 70%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ES%3C/text%3E%3C/svg%3E)
1 answer
Speech Studio Custom Model - Large Plain Text Dataset
Hi, I have a fairly large dataset of plain text names (300,000+) which I'd like to train a custom model for. I don't have pronunciation or audio form of the names, only plain text. My previous attempts to train a custom model with a sample of these…
asked 2021-08-18T09:33:27.123+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(76.8, 85%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EE2%3C/text%3E%3C/svg%3E)
evisnetnim-2
1
Reputation point
commented 2021-08-31T06:19:23.677+00:00
romungi-MSFT
44,581
Reputation points Microsoft Employee