diff --git a/speech/api/README.md b/speech/api/README.md
index 0998e67a493..a017e3276bf 100644
--- a/speech/api/README.md
+++ b/speech/api/README.md
@@ -72,6 +72,14 @@ for more information.
 
     You should see a response with the transcription result.
 
+* To run the `speech_async_rest.py` sample:
+
+    ```sh
+    $ python speech_async_rest.py resources/audio.raw
+    ```
+
+    You should see a response with the transcription result.
+
 * To run the `speech_streaming.py` sample:
 
     ```sh
diff --git a/speech/api/speech_async_rest.py b/speech/api/speech_async_rest.py
index c0ddbdb4cd5..a06102e6903 100644
--- a/speech/api/speech_async_rest.py
+++ b/speech/api/speech_async_rest.py
@@ -22,13 +22,12 @@
 import time
 
 from googleapiclient import discovery
+import httplib2
 from oauth2client.client import GoogleCredentials
 # [END import_libraries]
 
 
 # [START authenticating]
-DISCOVERY_URL = ('https://{api}.googleapis.com/$discovery/rest?'
-                 'version={apiVersion}')
 
 
 # Application default credentials provided by env variable
@@ -36,10 +35,10 @@
 def get_speech_service():
     credentials = GoogleCredentials.get_application_default().create_scoped(
         ['https://www.googleapis.com/auth/cloud-platform'])
+    http = httplib2.Http()
+    credentials.authorize(http)
 
-    return discovery.build(
-        'speech', 'v1beta1', credentials=credentials,
-        discoveryServiceUrl=DISCOVERY_URL)
+    return discovery.build('speech', 'v1beta1', http=http)
 # [END authenticating]