Adds the audio Speech API

* Adds a simple speech API testcase
* Adds a small documentation section

README.md

@@ -460,6 +460,22 @@ puts response["text"]
 # => "Transcription of the text"
 ```
 
+#### Speech
+
+The speech API takes as input the text and a voice and returns the content of an audio file you can listen to.
+
+```ruby
+response = client.audio.speech(
+  parameters: {
+    model: "tts-1",
+    input: "This is a speech test!",
+    voice: "alloy"
+  }
+)
+File.binwrite('demo.mp3', response)
+# => mp3 file that plays: "This is a speech test!"
+```
+
 ### Errors
 
 HTTP errors can be caught like this:

lib/openai/audio.rb

@@ -11,5 +11,9 @@ def transcribe(parameters: {})
     def translate(parameters: {})
       @client.multipart_post(path: "/audio/translations", parameters: parameters)
     end
+
+    def speech(parameters: {})
+      @client.json_post(path: "/audio/speech", parameters: parameters)
+    end
   end
 end

spec/openai/client/audio_spec.rb

@@ -55,5 +55,24 @@
         end
       end
     end
+
+    describe "#speech" do
+      context "with audio", :vcr do
+        let(:model) { "tts-1" }
+
+        it "returns a working mp3 file as body" do
+          VCR.use_cassette("speech #{model} test") do
+            response = OpenAI::Client.new.audio.speech(
+              parameters: {
+                model: model,
+                input: "This is a speech test!",
+                voice: "alloy"
+              }
+            )
+            expect(response).not_to be_empty
+          end
+        end
+      end
+    end
   end
 end