I wanted to know if you could add a Speech Client Library for Xamarin with features such as intermediate results during recognition.
When sending a request I get the InitialSilenceTimeout error with Duration and Offset both 0. That would indicate there is a problem with my audio file but that couldn't be true! I'm using WAV files with 16 bit PCM encoding and 16 kHz sampling rate. Could someone please tell me what could be the problem and/or point to a speech file or database that is proven to be working. Thank you!1 vote
Could you please check text "给我来点咖啡，谢谢。我们久仰贵公司的大名，那么它具体是何时成立的呢？". There is a distortion with the last the character 谢
We need a woman voice as the customers have branded bots (personas)29 votes
My name is Bert, I am a CSA working on the medical vertical for WE. Is there a roadmap available that contains the next supported languages for the Bing Speech Api. I am in need for Nordic and Dutch languages for hospitals.
Thanks for the great work and support! :)1 vote
Create a sample that works and remove all samples that don't work. I get Login Failed, then Transport Error 100% of the time.
Create a sample that works and remove all samples that don't work. I get Login Failed, then Transport Error 100% of the time.1 vote
I downloaded files from Github, ran npm install etc, but just kept receiving "Speech Recognition SDK not found"
Followed GitHub's direction for the download and install, got a new key from you, entered the key in each of the scripts that required keys. But continued to receive the same "Speech Recognition SDK not found" message even though I can see it in the directory as GitHub states. By the way, your 7 day FREE is lame.1 vote
I work for the company is very large, and they use speech recognition from Google, I want to check for them if Microsoft is better, but I ne
I work for the company is very large, and they use speech recognition from Google, I want to check for them if Microsoft is better, but I need to have language support for Hebrew.
Thank you very much.1 vote
I need to capture speaker voice immediately and feed it as input to the API instead of recording, converting to .wav, saving..etc
Hi, I am using Bing Speech API. For the Speech to Text I need to capture speaker voice immediately and feed it as input to the API instead of recording, converting to .wav mono 16-Bit 17 Khz format, saving....etc. We need user to speak and then program to capture speech immediately and pass it to the API.2 votes
I need to use Text To Speech API in my own voice. Is it possible to register a person's voice and use it for Text To Speech API
I need to use Text To Speech API in my own voice. Is it possible to register a person's voice and use it for Text To Speech API.
I have to register my voice.1 vote
More dialect driven english-based Quantum apis should be implemented perhaps do a screen testing or focus group study on heavily accented in
Perhaps the study group is needed here and perhaps several study groups from several different countries is needed as well all heavily speaking English1 vote
We have experienced very low quality/accuracy in en-in India English Language base models, mainly on the bidirectional conversations with noises, over-lap conversations, etc., mainly from the call centre audios, phone calls, mobile conversations.
uni-directional/one-way conversations like demo/webinar/presentations quality/accuracy is better as compared with the en-us USA English.
Early adaption of this service is being most awaited for our business requirements, willing to share the insights/sample audios files for analysis and improvements.2 votes
Please provide an option to block profane speech in Bing Speech-to-Text.1 vote
I'm new to Azure, and trying to use Text to Speech programmatically.
According to https://docs.microsoft.com/en-us/azure/cognitive-services/Speech/api-reference-rest/bingvoiceoutput#VoiceSynthesisRequest, I want to know how I get values of X-Search-AppId, X-Search-ClientID and User-Agent? And what does application mean in description? Should I get those values from Azure Portal, or just generate random ones?
Thanks in advance!2 votes
I want to get Japanese Kana;
But DisplayText and LexicalForm are same value;1 vote
We have a client that is upset because they received a call about one of their children whose name was pronounced wrong. The child's name was "Nicarri", but Bing pronounced it "Nicker", and the parent who received the call thought it was a racial slur.
I attached a recording of a test call (not the actual call).1 vote
I have been unable to implement the system in Java because there are no diagnostic messages to even give a hint as to where the streaming data I am sending is wrong. Hence I have given up and will use two other different APIs, both of which work.1 vote
Your SDK cannot be used with the vast majority of current Android hardware.
Your team has commented elsewhere (Github?) that you intend to open source this portion of the product rather than provide prebuilt binaries. If that's true could you give a date for when it will happen?1 vote
Please strong name the SpeechClient.dll so we can included in signed projects.1 vote
We know that Text to Speech is supported in Korean.
(Text to Speech: Korean - KR / HeamiRUS)
However, Speech to Text does not support Korean. Only English, Chinese, French, German, Italian, and Spanish are in the list. There is no Korean in the list. Please add Korean.7 votes
- Don't see your idea?