Difference between revisions of "Automated Speech Recognition"
Jump to navigation
Jump to search
(→Google Cloud Speech-to-Text API) |
|||
Line 10: | Line 10: | ||
# Create a Google Cloud API project | # Create a Google Cloud API project | ||
# Generate a private service account key JSON file | # Generate a private service account key JSON file | ||
− | # | + | # Download the JSON file, saving it on the robot as... |
<pre> | <pre> |
Revision as of 10:27, 17 May 2018
This is a protected page.
Speech to text is provided by the Speech Recognition Tritium node. The actual recognition is done by a configurable backend, with Google's Cloud Speech-to-Text API as the default (and currently only) option.
Google Cloud Speech-to-Text API
To use the API the node must provide authentication credentials.
The process to create new credentials is as follows
- Create a Google Cloud API project
- Generate a private service account key JSON file
- Download the JSON file, saving it on the robot as...
/opt/tritium/nodes/speech_recognition/google_application_credentials.json
The Before You Begin section of the Quickstart: Using Client Libraries tutorial covers this process. (You do not need to follow the rest of the tutorial.)