Differences

This shows you the differences between two versions of the page.

--- ttsproviders:polly [2018/02/15 17:26] – [AWS Client is required] javier
+++ ttsproviders:polly [2018/02/15 17:38] – [AWS Client Installation] javier
@@ Line 5: / Line 5: @@
 ** Polly from Amazon **
-Website: __[[https://aws.amazon.com/polly]]__
+  *Website: __[[https://aws.amazon.com/polly]]__
+  *Pricing: __[[https://aws.amazon.com/polly/pricing/]]__
 ===== Definition =====
@@ Line 11: / Line 12: @@
 Amazon Polly is a service that turns text into lifelike speech. Polly lets you create applications that talk, enabling you to build entirely new categories of speech-enabled products. Polly is an Amazon AI service that uses advanced deep learning technologies to synthesize speech that sounds like a human voice. Polly includes 47 lifelike voices spread across 24 languages, so you can select the ideal voice and build speech-enabled applications that work in many different countries.
-===== Get started =====
+===== Create AWS KeyID and Secret Key =====
-Create your account :
+From your AWS account you must create dedicated credentials
-  * [[https://console.api.ai/api-client/#|Console panel]]
 ===== AWS Client Installation =====
@@ Line 28: / Line 27: @@
 </code>
+Once aws-cli command is installed, you can check that it's working by using this command line, according to your credentials :
+<code>
+AWS_ACCESS_KEY_ID=XXXXXXXXXXXXXXXXXXXX \
+AWS_SECRET_ACCESS_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx \
+/usr/bin/aws  polly synthesize-speech    --output-format mp3    --voice-id Joanna    --text 'Hello my name us Joanna!' --region 'eu-west-1' hello.mp3
+</code>
+The result looks like :
+<code>
+{
+    "ContentType": "audio/mpeg",
+    "RequestCharacters": "5"
+}
+# file hello.mp3
+hello.mp3: Audio file with ID3 version 2.4.0, contains: MPEG ADTS, layer III, v2,  48 kbps, 22.05 kHz, Monaural
+</code>
 ===== Configuration =====