I am using microsoft's latest Botframework-webchat v4.5.2 from https://github.com/microsoft/BotFramework-WebChat. Is there a way to use a custom STT/ TTS like google or watson's STT/TTS. Note this was possible in v3 using the ISpeech interface. Is there an equivalent in v4?
Need to be able to use a custom speech to text, text to speech engine like google's or watson's in webchat v4
In webchat v3 this can achieved by implementing the ISpeechRecognizer and ISpeechSynthesizer interfaces and I was able to use it with google's STT and TTS
There are two samples on the BotFramework-WebChat repo that you should look over:
06.c.cognitive-services-speech-services-js: Introduces speech-to-text and text-to-speech ability using Cognitive Services Speech Services API.
06.f.hybrid-speech: Demonstrates how to use both browser-based Web Speech API for speech-to-text, and Cognitive Services Speech Services API for text-to-speech.
Either sample should give you the functionality you are looking for. You can review the complete list of Web Chat samples on their repo, located here.
Hope of help!
Related
I am trying to find more information, but I cannot get access to the API portal page https://www.projectoxford.ai/vision . Do you know if Microsoft is planning to remove the API?
ProjectOxford was deprecated in favor of Cognitive Services
The Vision API have the following main paths
Computer Vision
Analyze content in images and video.
Custom Vision
Customize image recognition to fit your business needs.
Face
Detect and identify people and emotions in images.
Form Recognizer
Extract text, key-value pairs, and tables from documents.
Video Indexer
Analyze the visual and audio channels of a video, and index its content.
DEV API reference of all services ➡ https://eastus.dev.cognitive.microsoft.com/docs/services/
I am exploring ways to improve some of our processes and applications using microsoft tools and more specifically the Custom Vision Cognitive Service. However, i am getting lost in the MS offerings and the Preview AI Builder service in PowerApps which seems to be offering the same capability.
The test that I am trying with both services i using Products pictures and utilize the services to provide me with the brand, sub-brand and some other specifications on the product. To start with, i have started with the browser version of the Custom Vision service (not the SDK) which, because it is a non-programmer interface, is really similar to the AI builder.
Has someone more inputs on the strategy behind the AI Builder in Powerapps and how it complements/replaces some of the capabilities of the MS cognitive services (and more specifically their browser/non-programmer versions)?
In a few words, tools in PowerApps (like in Microsoft Flow or even Logic Apps) are backed by other (more technical) services provided by Microsoft (or third party).
PowerApps and Flow are solutions designed to be used by non-developer people: understanding the technical behaviour / implementation is not needed.
Using AI Builder service in PowerApps vs Custom Vision: generally, there may be a delay between new technical features and the time they are provided in those tools for example. Some features are also never available in "business" versions.
I'm trying to build a sina app which will have capabilities of searching statuses based on key word, geo location, date etc...
I cannot find an api which supports what I'm trying to do.
I am aware they have a v1 api which does what I want but it is legacy and no longer accepting apps.
You are right that weibo has removed most of the content search api functionality in v2 of the api.
The api calls that are currently supported are listed here: http://open.weibo.com/wiki/API%E6%96%87%E6%A1%A3_V2/en#Search_API
Content search is labeled only for legacy applications that have good standing.
I am trying to develop a web based map application where the user can interact with the map. But I am new to this field and do not have much idea about how to approach this. Basically I want to use a static map created by me, so I think google map API s may not be used in this case. My development platform is unix. Can you please suggest what language I should use to write the server and also what kind of free tools can be used to implement the map part?
Thanx...
I suggest reading up on the Google Maps API 3. You can add overlays or even add your own tiles using the API. Specifically, I suggest looking into the GroundLayers section of the V3 API here GroundOverlays
I've got a Flex application that uses the Google Maps component. Is it possible to configure the component to use Google Maps API v3 without API Key? If not, is there a workaround to use the JavaScript API? Or a timeline for providing swc using Google Maps API v3?
I currently perform client-side geocoding using the Google Maps API v3 webservice, but I need to also display maps and allow user to interact with them.
Firstly, realize that the Javascript API and the Flash API are different API's.
I imagine that they will porting the no API key feature to the Flash API soon.
However, I have no used the Flash API in a while and Google may be moving away from maintaining it. It doubt that they will though. They have a lot invested in the Flash API.