A demo video of this project is available here.
The Speech to Text service uses IBM's speech recognition capabilities to convert speech in multiple languages into text. The transcription of incoming audio is continuously sent back to the client with minimal delay, and it is corrected as more speech is heard. The service is accessed via a WebSocket interface; a REST HTTP interface is also available;
Node.js is also used to provide the browser client's authentication token.
Give it a try! Click the button below to fork into IBM DevOps Services and deploy your own copy of this application on Bluemix.
-
Create a Bluemix Account
Sign up in Bluemix, or use an existing account. Watson Services in Beta are free to use.
-
Download and install the Cloud-foundry CLI tool
-
Edit the
manifest.yml
file and change the<application-name>
to something unique.
applications:
- services:
- speech-to-text-service-standard
name: <application-name>
command: node app.js
path: .
memory: 512M
The name you use will determinate your application url initially, e.g. <application-name>.mybluemix.net
.
-
Install Node.js
-
Install project dependencies and build browser application:
$ npm install && npm run build
- Connect to Bluemix in the command line tool.
$ cf api https://api.ng.bluemix.net
$ cf login -u <your user ID>
- Create the Speech to Text service in Bluemix.
$ cf create-service speech_to_text standard speech-to-text-service-standard
- Push it live!
$ cf push
See the full Getting Started documentation for more details, including code snippets and references.
The application uses Node.js and npm so you will have to download and install them as part of the steps below.
-
Copy the credentials from your
speech-to-text-service-standard
service in Bluemix toapp.js
, you can see the credentials using:$ cf env <application-name>
Example output:
System-Provided: { "VCAP_SERVICES": { "speech_to_text": [{ "credentials": { "url": "<url>", "password": "<password>", "username": "<username>" }, "label": "speech-to-text", "name": "speech-to-text-service-standard", "plan": "standard" }] } }
You need to copy
username
,password
andurl
. Then you need to pass those values in app.jsvar config = { version: 'v1', url: 'https://stream.watsonplatform.net/speech-to-text/api', username: '<username>', password: '<password>' };
-
Install Node.js
-
To install project dependencies, go to the project folder in a terminal and run:
$ npm install
-
Then, build the browser application using Browserify:
$ npm run build
-
Start the application:
$ node app.js
-
Go to: http://localhost:3000
To troubleshoot your Bluemix app the main useful source of information are the logs, to see them, run:
$ cf logs <application-name> --recent
For problems with recording audio, you can play back the audio you just recorded for debugging purposes. To do that, add '?debug=true' (without the quotations) in the URL.
This sample code is licensed under Apache 2.0. Full license text is available in LICENSE.
See CONTRIBUTING.
Find more open source projects on the IBM Github Page