refactor(ai): add T2S docker image instructions (#685)

This commit adds instructions for downloading the T2S docker image to the T2S pipeline packge so that orchs don't forget to download this image when trying to serve T2S image models.

---------

Co-authored-by: Rick Staa <[email protected]>

Author: papabear99

ai/pipelines/text-to-speech.mdx

@@ -64,6 +64,17 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 12GB** of
   VRAM.
 
+### Pipeline-Specific Image
+
+To serve the `text-to-speech` pipeline, you must use a pipeline specific AI
+Runner container. Pull the required container from
+[Docker Hub](https://hub.docker.com/r/livepeer/ai-runner/tags?name=text-to-speech-latest)
+using the following command:
+
+```bash
+docker pull livepeer/ai-runner:text-to-speech
+```
+
 ## API Reference
 
 <Card