Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
1 answer
CRITICAL ISSUE Azure AI Speech SDK – Numbers getting Added , Deleted and Substituted and sometimes Exceeds too much time while using the microsoft realtime speech to text conginitve services API
We are using Azure Speech Service with the browser Speech SDK for real-time speech-to-text transcription. We are observing an issue when users speak continuous digits. The recognizer sometimes returns a significantly different number of digits than were…
Azure AI Speech
asked 2026-03-06T14:12:10.9733333+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(272, 69%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAK%3C/text%3E%3C/svg%3E)
Aravind ks
20
Reputation points
edited a comment 2026-03-12T16:01:14.14+00:00
Aravind ks
20
Reputation points
2 answers
Speech Studio Text to Speech - Silence Not Working
I'm trying to add silence in my text to speech files (see image below), but the silence tags will not actually generate the specified silence where I input them when I preview the audio. The silence doesn't show up in the exported output either. Am I…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2025-12-23T17:34:12.06+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(73.60000000000001, 74%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKD%3C/text%3E%3C/svg%3E)
Kika D
0
Reputation points
answered 2026-03-12T13:31:19.62+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, 22%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EI%3C/text%3E%3C/svg%3E)
IngallsPW1
41
Reputation points
1 answer
Cohere Rerank v4.0 Fast returns 500 error in Azure AI Foundry when using DefaultAzureCredential
Hi, I am experiencing persistent 500 Internal Server Error issues when using Cohere Rerank v4.0 Fast in Azure AI Foundry. I have carefully followed the guidance provided in similar threads: Verified the exact deployment name:…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-11T14:46:04.52+00:00
Arne Lieten
0
Reputation points
answered 2026-03-11T16:13:52.5033333+00:00
Vinodh247
41,566
Reputation points MVP
Volunteer Moderator
1 answer
One of the answers was accepted by the question author.
Deploy Azure AI Speech with CognitiveResource or Microsoft Foundry
Someone any information on if we should deploy AI Speech via microsoft.cognitiveservices/accounts or new via MicrosoftFoundry? Will the microsoft.cognitiveservices/accounts be deprecated? The old speech studio at least doesn't seem to support…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-11T14:20:09.4166667+00:00
Nathanael Santschi
156
Reputation points
accepted 2026-03-11T14:22:47.9366667+00:00
Nathanael Santschi
156
Reputation points
1 answer
Special character ampersand (“&”) breaks word boundaries in Azure Text-to-Speech
Hello, I’m encountering an issue with word boundary events in Azure Text-to-Speech when the input text contains the ampersand character (&). Context Locale: fr-FR Neural French voice (e.g. fr-FR-Remy:DragonHDLatestNeural) Batch synthesis API …
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-26T10:51:25.2866667+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(227.2, 53%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESM%3C/text%3E%3C/svg%3E)
Soulaïman Marsou
0
Reputation points
commented 2026-03-11T06:09:16.52+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(176, 16%, 27%)' 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)
SRILAKSHMI C
15,030
Reputation points Microsoft External Staff
Moderator
2 answers
Pronunciation Assessment with Language en-GB- Phoneme symbols
I am using the pronunciation assessment API for language en-GB Doing the assessment at phoneme level The documentation does mention this: AccuracyScore: Phoneme level， Syllable level (en-US only)， Word level， Full Text level I get a response with empty…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-18T17:07:02.75+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(272, 57.99999999999999%, 36%)' 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)
Anju Aggarwal
0
Reputation points
commented 2026-03-08T22:20:21.45+00:00
Anju Aggarwal
0
Reputation points
1 answer
Issue Creating Azure AI Language Resource in Custom Question Answering Lab
Hello, I am currently working on the Microsoft Applied Skills lab for Custom Question Answering. When attempting to create the Azure AI Language resource, the deployment fails with the following error: RequestDisallowedByPolicy – The resource was…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-08T05:34:50.2333333+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(307.2, 92%, 39%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EPC%3C/text%3E%3C/svg%3E)
Pornpra Chumnanvanichkul
0
Reputation points
answered 2026-03-08T20:32:29.5466667+00:00
Divyesh Govaerdhanan
10,610
Reputation points
2 answers
Please clarify the conflicting information regarding permission to use the free tier of Azure Speech for commercial purposes, such as narration of a YouTube video.
Hello everyone, I had previously asked a question on this forum regarding whether the Free Tier F0 of Azure Speech can be used for commercial purposes such as narration of a YouTube video:…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-03T07:28:30.2+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(163.2, 43%, 25%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EK%3C/text%3E%3C/svg%3E)
KRJ14
0
Reputation points
commented 2026-03-05T01:09:38.88+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(204.8, 15%, 29%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMM%3C/text%3E%3C/svg%3E)
Manas Mohanty
15,295
Reputation points Microsoft External Staff
Moderator
1 answer
Can the audio generated by Azure Speech Studio's free tier (monthly limit of 500,000 characters) be used for commercial purposes like for example: narration of a youtube video?
Hello! I've searched this Q&A site extensively but found conflicting answers and hence, I thought I should I ask directly. I've Azure Speech Studio's free tier (monthly limit of 500,000 characters) and can I use the audio generated by that for…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-01T05:39:56.72+00:00
KRJ14
0
Reputation points
commented 2026-03-03T17:40:30.41+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(291.2, 38%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMP%3C/text%3E%3C/svg%3E)
Marcin Policht
82,360
Reputation points MVP
Volunteer Moderator
2 answers
Custom Neural Voice (CNV Pro) model in East US and East US 2 is failing to train the model
Custom Neural Voice (CNV Pro) model in East US and East US 2, and the training consistently fails after several hours with an internal/unknown error. The dataset uploads successfully and passes validation, but the training job never completes. It fails…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-01T17:26:01.8533333+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(112.00000000000001, 41%, 20%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERI%3C/text%3E%3C/svg%3E)
Ramachandran, Iaiswarya I
20
Reputation points Microsoft Employee
commented 2026-03-03T14:29:12.7+00:00
Ramachandran, Iaiswarya I
20
Reputation points Microsoft Employee
2 answers
Azure AI Foundry agents intermittently failing with JSON parsing error (empty response, no schema changes)
We are experiencing intermittent but increasingly frequent failures when running agents on Azure AI Foundry. Agents that were working correctly in the same environment, with no code or schema changes, suddenly started failing with the following…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-26T13:01:19.7233333+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(38.4, 25%, 13%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMG%3C/text%3E%3C/svg%3E)
Maximiliano Gutierrez
5
Reputation points
edited the question 2026-03-02T18:17:38.46+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(51.2, 6%, 14%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJH%3C/text%3E%3C/svg%3E)
Jilakara Hemalatha
10,365
Reputation points Microsoft External Staff
Moderator
2 answers
Python code to generate ephemeral token for gpt-4o-mini-transcribe OR gpt-4o-transcribe
Hi Team, We're unable to find ways/python code to generate ephemeral token for gpt-4o-mini-transcribe OR gpt-4o-transcribe. Searched online & there are some references for generating such tokens for realtime API. But none for…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-25T12:42:59.1733333+00:00
GenixPRO
176
Reputation points
answered 2026-03-02T16:47:22.3466667+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(28.799999999999997, 15%, 12%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAV%3C/text%3E%3C/svg%3E)
Anshika Varshney
7,995
Reputation points Microsoft External Staff
Moderator
2 answers
can some one help, how to config voicelive sdk to recieve animation blendshapes and viseme_id
it try to add this but no animation data recieve. modalities: ["text", "audio", 'animation'], outputAudioTimestampYypes: ["word"], animation: { modelName: "default", outputs:…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-25T17:09:02.8933333+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(272, 89%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDH%3C/text%3E%3C/svg%3E)
Dadong Hu
0
Reputation points
commented 2026-03-02T12:30:00.6933333+00:00
Anshika Varshney
7,995
Reputation points Microsoft External Staff
Moderator
1 answer
Has MS abandoned human tech support?
Reading some of the nightmare scenarios on these forums and realizing that human tech support is a thing of the past really alarms me. It's obvious that since companies such as MS are pouring so much into AI, they've abandoned tech support from humans.…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-03-01T21:28:29.3033333+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(153.6, 97%, 24%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EEM%3C/text%3E%3C/svg%3E)
Ed Myers
0
Reputation points
answered 2026-03-02T00:29:40.7033333+00:00
Jerald Felix
10,975
Reputation points
1 answer
Issues with Azure Speech Services: Incorrect transcription of "draft" as "draught" and "£" as "lbs" in UK English
I'm using Azure Speech Services with the language set to UK English, and I've noticed two recurring transcription issues: When I dictate the word "draft", it consistently transcribes as "draught", even when the context clearly favors…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2025-06-12T11:36:24.3566667+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(201.6, 88%, 29%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ENK%3C/text%3E%3C/svg%3E)
Niki Kariappa
0
Reputation points
answered 2026-03-01T23:36:12.31+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(307.2, 71%, 39%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMW%3C/text%3E%3C/svg%3E)
Mike Williams
0
Reputation points
1 answer
High Initial Latency with Multi-Language Detection (3+ Languages)
Hello Azure Speech Team, We're experiencing significant initial latency when using Continuous Language Identification with 2+ languages in production. Configuration: Languages: 3 languages (en-IN, te-IN, hi-IN) Mode:…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-14T10:23:11.7166667+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(172.8, 92%, 26%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EEA%3C/text%3E%3C/svg%3E)
ello ai
5
Reputation points
commented 2026-02-25T07:32:16.5566667+00:00
SRILAKSHMI C
15,030
Reputation points Microsoft External Staff
Moderator
2 answers
gpt-4o-transcribe for real-time speech-to-text transcription ---slow speed
When I try to use gpt-4o-transcribe for real-time speech-to-text transcription, it takes about 1.5-2 seconds for a 2s mp3 file from sending the request to receiving the first token. Are there improved methods or other model options? Additionally,…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-24T03:40:45.7033333+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(64, 14.000000000000002%, 16%)' 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)
yu.lili
0
Reputation points
answered 2026-02-25T06:25:07.45+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(6.4, 51%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKV%3C/text%3E%3C/svg%3E)
Karnam Venkata Rajeswari
300
Reputation points Microsoft External Staff
Moderator
1 answer
Custom Avatar Model Training Showing as Processing After 16 Hours
I created a Azure AI Service Resource in West US 2(Test Avatar) and then went to Speech Studio, uploaded all the required training Data and then started the model training. But its showing 1hr left estimated for last 8 Hours.
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-25T02:16:06.2066667+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(67.2, 33%, 16%)' 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)
Trinanjan Majumder
0
Reputation points Microsoft Employee
answered 2026-02-25T03:38:09.5266667+00:00
SRILAKSHMI C
15,030
Reputation points Microsoft External Staff
Moderator
3 answers
Transcription using gpt-4o-transcribe with gpt-realtime is failing in useast2
Hello, I am trying to use gpt-4o-transcribe with gpt-realtime in useast2, and it is consistently failing. I am using gpt-realtime with websockets as per the documentation. I am seeing the following event:…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-12T08:11:59.3233333+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(12.8, 17%, 11%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EPW%3C/text%3E%3C/svg%3E)
PRABU WEERASINGHE
0
Reputation points
commented 2026-02-24T12:47:18.32+00:00
SRILAKSHMI C
15,030
Reputation points Microsoft External Staff
Moderator
2 answers
One of the answers was accepted by the question author.
Pricing for Azure Voice Live API
We are evaluating Azure Voice live API for our Contact Center use case, automating with AI. However, we could not find the latest pricing of Azure Voice live API - we want to use Pro version - use Azure speech, GPT 5.2 Chat (or suitable chat models).…
Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
2,299 questions
asked 2026-02-17T12:53:48.97+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(102.4, 23%, 19%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESR%3C/text%3E%3C/svg%3E)
Sankar Ramakrishnan, Prathap
20
Reputation points
accepted 2026-02-24T05:09:15.0766667+00:00
Sankar Ramakrishnan, Prathap
20
Reputation points