Confused on custom neural voice docs
Hi all, I'd like to implement custom text to speech voices and I was pleased to see that azure offers different solutions, but i'm confused on the types of services. In the docs page I saw 3 types of custom speech methods: pro, lite and personal but in…
When is the GA release for customization of Avatars in Microsoft TTS Avatar service and non-photorealistic options for custom avatars
Two part question on the TTS Avatars When is the TTS Avatar - customization of Avatars going to be GA ? How can we do non-photorealistic Avatars (i.e, Animated/Cartoon characters like the Microsoft Mesh)?
How to use private endpoint for Azure speech resource in realtime
We have used below documenation which provide details of realtime transcription using speech SDK. https://zcusa.951200.xyz/en-us/azure/ai-services/speech-service/get-started-stt-diarization?tabs=linux&pivots=programming-language-python We…
Delay in Transcription (Multi-Device Conversation) Cognitive Speech
As the documentation says that multi device conversation is real time but running the sample code there is delay of about 12 - 15 second in transcribing. How can i make it real time??
Azure AI Speech Studio TextToSpeech with voice "AlloyTurboMultilingual" shows "Error 400 Synthesis failed. StatusCode: NotFound"
Inside of Azure AI Speech Studio when trying to generate speech with the voice "AlloyTurboMultilingual" or "NovaTurboMultilingual" the following error occurs: Response status code does not indicate success: 400 (Synthesis failed.…
Is there GRPC support for Speech to Text in Azure Speech SDK in java?
Hi, Is there GRPC support for Azure speech SDK? We are looking for this support for the Realtime Speech to Text feature. Is that support available in Java? If there is no GRPC support, what is the underlying architecture, and how is the voice streamed to…
Issue with Continuous Language Identification in Azure Speech SDK for Angular Application
We are currently using the "microsoft-cognitiveservices-speech-sdk" in our Angular application (version 14) for speech transcription and translation. The transcription and translation functionality is working as expected. However, we are…
Adjusting Audio Speed in Azure AI Speech
Is it possible to adjust the speed of audio generated using an OpenAI voice? I know that OpenAI's REST API supports a parameter for speed, but I couldn't find anything similar in the Azure AI Speech documentation. Thanks in advance!
Can I set maximum number of participants to real-time diarization?
Hi, I follow the document below and success to distinguish the speaker with audio streaming by ConversationTranscriber Class. (I don't use voice signature so it shows Guest-1,…
speech api fails where Speech Studio succeeds?
I am using the Standard Tier, with a couple paragraphs of text and only a few ssml tags. The ssml pasted into Speech Studio renders correctly, even exports to an audio file correctly. The same ssml rendered through the python API causes the error below.…
I can't create a simple support ticket to increase my text to speech concurrency request limit
I want to increase my text to speech concurrency request and TPS limit but Microsoft wouldn't allow me to create a support ticket but instead wants me to buy a plan to contact support. I am already on Standard S0 Tier.
Why is speakTextAsync() occasionally silent?
I am using the following Javascript code to test Azure TTS. It works well, but about 1 in 10 times, when called, it produces no sound despite logging "Synthesis finished" as expected. The next time it is called, the sentence "Good morning,…
I am locked out of my account. I don't know what to do.
I just tried to log into my account and it says i am locked out and I should contact my support person. First, i do not know why i am being locked out. Second, i do not have a support person or who to contact about this. Any help please? See attached…
Transcription Denormalization.
Is there a way to "denormalize" Azure speech transcription, so it provides verbatim transcription (as close as possible, with word fillers, hesitations, repeats, etc)? I will also need word level timestamping and diarization. I am hoping there…
I can't create a simple support ticket to increase my text to speech concurrency request limit
I want to increase my text to speech concurrency request and TPS limit but Microsoft wouldn't allow me to create a support ticket but instead wants me to buy a plan to contact support. I just need to increase my limit. Can someone please here from here?
Do we have any API Support to get the cost estimation of Audio Translation?
Do we have any API Support to get the cost estimation of audio translation from language to another language by taking input as audio duration, source language, target language, etc., required input. If any API support in java, please help me Thanks…
looking for python code examples for fast transcription api
can you please share some python code examples for fast transcription api ? I can't find much...
azure speech to text only transcribe about 50% of the audio
I am using the speech to text but only able to transcribe about 50% of the audio. (ms word is able to transcribe the entire audio file) audio file is wav, only 2 min and 15 sec, size: 2112 kb this is my first time using this. Is there any setting that…
How to Stream Chat API Response Directly to Azure TTS Avatar for Continuous Speech?
I'm currently working on integrating Azure Text-to-Speech (TTS) with an avatar system. Right now, the avatar only starts speaking after receiving the entire chat response. Here is the relevant part of the code I'm using: const handleSpeak = () => { …
[Multi Device Conversation] - [Multi-Device Conversation][DotNet] Cannot set display name/Nickname when join conversation.
Hi, I tried to implement the code according to the example at the link: https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/quickstart/csharp/dotnet/multi-device-conversation/helloworld/Program.cs. But when I set display name…