Updating the text2speech readme

@ZanSara I noticed the 'Usage' section was missing even though it was listed here. I also created this PR for the integrations page, would be great if you can review. That one is just an index repo for the website: deepset-ai/haystack-integrations#14

nodes/text2speech/README.md

@@ -13,22 +13,38 @@
 
 ## Installation
 
+
+Only for Debian-based systems: first install the audio system dependencies:
+```console
+sudo apt-get install libsndfile1 ffmpeg
+```
+
+Install the text2speech package:
 ```console
 pip install farm-haystack-text2speech
 ```
 
-## Installation
 
-Step 1. Install the audio system dependencies. On Debian-based systems:
+## Usage
 
-```console
-sudo apt-get install libsndfile1 ffmpeg
-```
+For a full example of how to use the `AnswerToSpeech` Node, you may try out our "[Make Your QA Pipelines Talk Tutorial](https://haystack.deepset.ai/tutorials/17_audio)"
 
-Step 2. Install the package. With pip:
+For example, in a simple Extractive QA Pipeline:
 
-```console
-pip install farm-haystack-text2speech
+```
+from haystack.nodes import BM25Retriever, FARMReader
+from text2speech import AnswerToSpeech
+
+retriever = BM25Retriever(document_store=document_store)
+reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
+answer2speech = AnswerToSpeech(
+ model_name_or_path="espnet/kan-bayashi_ljspeech_vits", generated_audio_dir=Path("./audio_answers")
+)
+
+audio_pipeline = Pipeline()
+audio_pipeline.add_node(retriever, name="Retriever", inputs=["Query"])
+audio_pipeline.add_node(reader, name="Reader", inputs=["Retriever"])
+audio_pipeline.add_node(answer2speech, name="AnswerToSpeech", inputs=["Reader"])
 ```
 
 ## License