![]() ![]() The beta version came with the Web Speech API with voice support, a new tab page with a search box and blocking of silent extension installations. In January, Google launched Chrome 25 Beta for the desktop version of the browser and teased several new features that it said could be a part of the more stable release. Google's Aaron Koblin writes, "We hope that developers will find many uses for the Web Speech API, both fun and practical-including new ways to navigate, search, enter text, and interact with the web. ![]() Additionally, they can show off their skills to their friends by sharing it with them. Once the short clip ends, users have the option of either viewing what they've created or starting over. From there on, as users speak, they will watch the text appearing on their screen. For starters though, you will have to try saying "Action" to check if your microphone is in place and working. This brought me to thinking, what if I distributed a Chrome (not Chromium) browser, so the bonafide Google Chrome browser, but added an "extension" to it that allowed javascript within a custom html5 web page to interface with other applications on the client's system (ie a Node.js app running alongside this special installation of Chrome) and wrote my speech recognition portion in Javascript, Web Speech API style, and piped the output into the other application I design and have installed on clients' systems.Go to to begin with, and you can start almost as soon as you pick a movie clip of your choice. I was trying to think of a way to access Google's superior speech recognition technology on the desktop in my own app (language doesn't matter but node.js would likely be part of the mix so a node.js solution would be preferred) without this limit and that brought me to consider the Web Speech API standard which Google Chrome happens to implement.Īs far as I know, there is not a hard request/day limit imposed on Google Chrome's implementation of the Web Speech API, and I could happily write websites that used Web Speech API all day long without or with minimal restrictions compared to Google Speech API direct. Multiply that by a few hundred users and I'd be easily exceeding 50 requests/day. I see up to 500 requests/day by an individual desktop user if the voice recognition is broken up somehow, and most of these would probably be long-polling/continuous so maybe it'd only be 2 or 3 requests/day but hours at a time. ![]() I would like to write a desktop application that utilizes Google's speech recognition technology, but the 50 requests/day limit is unacceptable for wide distribution and even for a single desktop deployment of my envisioned software. There are also PHP libraries and Java libraries for accessing Google's Speech API, also requiring this key. To get that key you must subscribe to the newsgroup, and then follow a few steps and Google will give you a developer's key that is "not for distribution." The key is rate limited for 50 requests/day.įor example, node-google-speech-api outlines the need for having this key for a node application to access Google's Speech API directly (without the use of a browser): To use Google's Speech API directly it is now required that you obtain an API key. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |