2,336 questions with Azure Speech in Foundry Tools tags

Sort by: Updated
2 answers

Azure IVR Message Recording Capability Questions

We are a state‑level agency in the Commonwealth of Virginia currently evaluating enterprise‑grade Voice‑to‑Text, Text‑to‑Speech, and Speech Translation capabilities. Our existing environment is built on AWS, but we are exploring cross‑cloud options to…

Azure Speech in Foundry Tools
asked 2026-05-14T20:37:49.71+00:00
Lester, Gregory (VEC) 0 Reputation points
answered 2026-05-15T12:44:34.2533333+00:00
kagiyama yutaka 2,590 Reputation points
1 answer

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 …

Azure Speech in Foundry Tools
asked 2026-05-14T15:42:42.7033333+00:00
tomoe 0 Reputation points
answered 2026-05-14T15:43:04.94+00:00
Q&A Assist
1 answer

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

Azure Speech in Foundry Tools
asked 2026-05-07T11:43:41.7+00:00
Arne De Proft 0 Reputation points Microsoft Employee
edited an answer 2026-05-14T14:25:42.7066667+00:00
Sina Salam 28,691 Reputation points Volunteer Moderator
2 answers

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.…

Azure Speech in Foundry Tools
asked 2026-05-13T02:23:17.26+00:00
Yin Chenqiao 0 Reputation points
answered 2026-05-13T22:22:55.29+00:00
Amanda Zhu 80 Reputation points
0 answers

Significant Regression in Code-Switching (EN-ZH) recognition for zh-HK after April 2026 Engine Update

Problem Description We are reporting a critical regression in the Cantonese (zh-HK) Speech-to-Text service that started occurring after the March 31, 2026 API retirement and the subsequent rollout of the latest engine (MAI-Transcribe-1). The Issue:…

Azure Speech in Foundry Tools
asked 2026-04-22T11:53:03.27+00:00
Peter Ng 0 Reputation points
commented 2026-05-13T22:20:41+00:00
Manas Mohanty 16,755 Reputation points Microsoft External Staff Moderator
1 answer

The v1 real-time STT endpoint returns a constant Confidence value of 0.039347406 for all NBest results globally.

The v1 real-time Speech-to-Text endpoint (/speech/recognition/{mode}/cognitiveservices/v1) returns a fixed Confidence value of 0.039347406 in the NBest array for every recognition result, regardless of audio quality, region, resource type, or SDK…

Azure Speech in Foundry Tools
asked 2026-04-23T13:50:50.8333333+00:00
OneReachAdmin-8533 0 Reputation points
commented 2026-05-13T17:27:48.48+00:00
Manas Mohanty 16,755 Reputation points Microsoft External Staff Moderator
1 answer

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

Azure Speech in Foundry Tools
asked 2026-05-11T11:17:54.2033333+00:00
Amrutha M 0 Reputation points
commented 2026-05-13T07:38:56.4366667+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator
0 answers

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…

Azure Speech in Foundry Tools
asked 2026-05-11T13:10:15.0633333+00:00
Hristijan Stefov 0 Reputation points
commented 2026-05-12T11:09:49.2633333+00:00
Hristijan Stefov 0 Reputation points
1 answer

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…

Azure Speech in Foundry Tools
asked 2026-05-05T19:20:38.75+00:00
Ming-Li Lin 0 Reputation points
commented 2026-05-08T12:30:01.3933333+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator
2 answers

Azure text-to-speech-avatar not yet available for deployment

I want to try out the Azure text-to-speech-avatar model, but when I select the model for deployment in the AI Foundry, I see a message "model is not yet available for deployment". This happened both in the West Europe region and in the Sweden…

Azure Speech in Foundry Tools
asked 2026-05-08T09:12:25.8233333+00:00
Janneke van de Loo 5 Reputation points
answered 2026-05-08T10:38:11.0033333+00:00
Anshika Varshney 10,655 Reputation points Microsoft External Staff Moderator
2 answers

Documentation question: Does Microsoft Stream transcription on SharePoint use Azure AI Speech?

Hello, I'm working on a research project that requires me to accurately describe the technology stack used for transcription within Microsoft 365, and I'm hoping you can help me clarify a technical question that I have not been able to confirm through…

Azure Speech in Foundry Tools
asked 2026-05-05T02:38:37.7733333+00:00
Catherine M. Stockdale 0 Reputation points
commented 2026-05-07T10:47:30.2933333+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator
1 answer

Next practical step is an Azure Support request for Speaker Recognition gated access for subscription?

One blocker remains, and it is on Azure’s side: the live Speaker Recognition smoke test returns 401 Unauthorized saying the subscription is not approved for the gated Speaker Recognition service. The resource/key are valid enough to exist and be mounted,…

Azure Speech in Foundry Tools
asked 2026-04-30T20:58:48.1566667+00:00
Lucy Noble 0 Reputation points
commented 2026-05-07T08:34:42.2266667+00:00
Anshika Varshney 10,655 Reputation points Microsoft External Staff Moderator
2 answers

What is Azure equivalent for input_audio_noise_reduction ?

We have moved from OpenAI deployed Realtime Mini 4o to Azure deployed Realtime 4o Mini. In OpenAI we had input_audio_noise_reduction property. But this property is not available in Azure deployment. What is the Azure OpenAI equivalent of this property?

Azure Speech in Foundry Tools
asked 2026-04-28T10:41:37.26+00:00
Divjot Singh 20 Reputation points
commented 2026-05-07T00:36:17.8466667+00:00
Manas Mohanty 16,755 Reputation points Microsoft External Staff Moderator
2 answers

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*)…

Azure Speech in Foundry Tools
asked 2026-05-06T11:56:36.1733333+00:00
Li Wangbiao 0 Reputation points
answered 2026-05-06T11:58:31.5166667+00:00
Li Wangbiao 0 Reputation points
1 answer

What dialect of Irish are the speech studio text to speech models (Colm and Orla) modeled after?

I am interested in learning more about Speech Studio's text to speech models for the Irish language. Currently, there are two available voices on the platform (Colm and Orla) which are labelled under Irish (Ireland). The Irish language does not have an…

Azure Speech in Foundry Tools
asked 2026-05-05T12:22:29.87+00:00
Sean McGoff 0 Reputation points
answered 2026-05-05T17:58:33.65+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator
1 answer One of the answers was accepted by the question author.

Joanne, the Australian female voice

Hi there, My name is Jacqui, and I use an eyegaze system with voice output due to living with severe Cerebral Palsy, a physical disability, and I’m non-verbal. I’ve been searching for an updated Australian female voice for over two years now. I’ve had…

Azure Speech in Foundry Tools
asked 2025-08-31T05:57:23.24+00:00
Jacqui Rogers 20 Reputation points
commented 2026-04-30T16:27:03.9533333+00:00
Georgia Kate Haege 0 Reputation points
1 answer One of the answers was accepted by the question author.

Test: Azure Speech Service Not Available in Foundry Tools

Question: I’m attempting to use Azure Speech services through Foundry tools, but the option does not show up or fails during setup. Details: Azure Speech resource is active Using Foundry Tools interface No clear error message, just missing or…

Azure Speech in Foundry Tools
asked 2026-04-28T21:01:13.8433333+00:00
Abhinava Maddha 105 Reputation points Microsoft Employee
accepted 2026-04-28T21:01:33.2066667+00:00
Abhinava Maddha 105 Reputation points Microsoft Employee
1 answer One of the answers was accepted by the question author.

Azure Cognitive Services TTS fails to generate audio for certain Unicode characters (e.g., em dash, arrow symbols)

I'm using Azure Cognitive Services Text-to-Speech (via SSML) to generate audio from text content. Some Unicode characters cause the TTS engine to fail or produce no audio output, while others in the same Unicode block work correctly. Characters that…

Azure Speech in Foundry Tools
asked 2026-04-23T18:55:50.31+00:00
Pawel Pelka 20 Reputation points
accepted 2026-04-28T17:17:42.65+00:00
Pawel Pelka 20 Reputation points
2 answers

Microsoft Foundry Speech Playground shows "Connection error to Realtime service: Invalid response status"

I had been using the "gpt-4o-realtime-preview" speech-to-speech model in the past months without issues. However since a few days it stopped working, not just in my python project but even in the Microsoft Foundry > Speech Playground: When I…

Azure Speech in Foundry Tools
asked 2026-04-19T15:15:09.15+00:00
Phil Nylund 0 Reputation points
commented 2026-04-28T13:53:31.5733333+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator
2 answers

Specifying a model in TranscriptionOptions of TranscriptionClient

Hi I am using a code similar to the one found in: link However when I specify a model in TranscriptionOptions options = TranscriptionOptions( locales=["en-US"], enhanced_mode=enhanced_mode, models={ "en-US":…

Azure Speech in Foundry Tools
asked 2026-04-22T04:51:08.1066667+00:00
Roy Aad 0 Reputation points
answered 2026-04-25T07:39:49.2866667+00:00
SRILAKSHMI C 18,225 Reputation points Microsoft External Staff Moderator