I am working on web speech recognition.
And I found that Google provide a API which call "Google speech API V2" to developer. But I notice there is a limit on every day to use it.
After that I found there is a native WEB Speech API also can implement the speech recognition. And it just working on google chrome and opera:
http://caniuse.com/#feat=speech-recognition
So
1. What is the different Google Speech API and Web Speech API? Are they have any relations?
The speech recognition result json is return from google. Is that the google speech api will be more accurate than web speech api?
Thank you.
The Web Speech API is a W3C supported specification that allows browser vendors to supply a speech recognition engine of their choosing (be it local or cloud-based) that backs an API you can use directly from the browser without having to worry about API limits and the like. You could imagine that Apple might power this with Siri and Microsoft might power this with Cortana. Again, browser vendors could opt to use the built in dictation software in the operating system, but that doesn't seem to currently be the trend. If your trying to perform simple speech synthesis in a browser (e.g. voice commands), this is likely the best path to take, especially as adoption grows.
The Google Speech API is a cloud-based solution that allows you to use Google's speech software outside of a browser. It also provides broader language support and can transcribe longer audio files. If you have a 20min audio recording you want to transcribe, this would be the path to take. As of the time of this writing, Google charges $0.006 for every 15s recorded after the first hour for this service.
The Web API is REST based API with API key authentication, especially for web pages which needs a a simple feature set.
While Google Speech API basically is a gRPC API with various authentication method. There are lot feature is available when you use gRPC, like authentication, faster calling, and streaming!!!
Related
Is there any way to get the actual recorded audio input from a Google Assistant or Amazon Alexa device to use in my own API backend?
This answer regarding the Android Speech Recognition API mentions that it's not really possible to get the audio recording.
While the platform provides a developer with the user transcription, it does not provide the underlying audio that generated the query.
My app has a list of fixed paragraphs that needs to be translated into speech. I plan to use Google's Text-to-Speech API to convert them into speech then download their audio files so that I don't need to constantly communicate with the API to translate them, considering that the paragraphs, once again, do not change.
Does this violate the Google Cloud Terms of Service restrictions?
Good news. It seems that caching synthesized audio files to avoid re-synthesization and promote cost saving is allowed with Google Text-to-Speech, as promoted by one of their use cases.
I'm interested in using Actions and the Assistant to create dynamic dialog for a video game.
Specifically I would want players to be able to speak (literally) to characters and for the characters responses to be determined by Actions, just like the Assistant.
Is there any version of the Assistant available that can be integrated into a game? As far as I can see they offer a lot of the building block services to developers, through the cloud, but nothing as fully featured as Google Assistant
Sounds like a cool scenario. Not something Actions on Google supports directly, but if you want to experiment, you could use the Google Assistant SDK to host the Assistant in your game and respond to queries that are meant for your players.
https://developers.google.com/assistant/sdk/
Love to see what you come up with.
It pretty much comes down to which Framework you use when building your game. If you use Unity for instance, you can use API.AI's Unity SDK.
There are also a lot of other SDKs provided. I don't think you really have to include the complete Google Assistant SDK, since you most likely will want to write your own responses (?). Some SDKs have speech recognition included, for others you will need a Speech Recignition framework, for instance Google Cloud Speech API.
Does Google speech API v2 support audio streaming via web sockets?
I found a way to send POST request with audio. However, it would be great if I can write audio and send it via socket in real time.
Note: I use Firefox browser. I know that Google Chrome supports voice recognition from the box, however I'm interested in Firefox and other browsers.
V2 of the API currently does not support web sockets. The streaming API uses gRPC which would need a translation layer to work with websockets.
https://cloud.google.com/speech/reference/rpc/google.cloud.speech.v1beta1#google.cloud.speech.v1beta1.Speech.StreamingRecognize
IBM Bluemix does support websockets, check out this sample project to see it in use: https://github.com/triceam/IBMWatson-QA-Speech/blob/master/config/socket.js
we have to develop a commercial video streaming application for iPhone & within that app we are planning to integrate additional searching functionality for Google Video & You Tube. I want to know following points,
Where can i find the Google video API & You Tube API ?
Will there be any legal issue on Google Video & You Tube video integration on commercial products, Form whom we have to the approval? Is there any standard procedure on this
You are allowed to do this but there are some restrictions
Take a look at the Terms of Service Point 1.2 Commercial Usage and Using the YouTube APIs to Build Monetizable Applications (too much to include in this answer)
Objective-C APIs for Google services are at http://code.google.com/p/gdata-objectivec-client/
YouTube provides an API, including video searches; Google Video does not.
Google APIs are intended for use in commercial applications, but carefully read the YouTube FAQ and the associated terms of services documents.