docs: updates

Author: mudler

docs/content/getting_started/_index.en.md

@@ -155,6 +155,8 @@ You can run `local-ai` directly with a model name, and it will download the mode
 | Embeddings | bert-cpp | ```docker run -ti -p 8080:8080 localai/localai:{{< version >}}-ffmpeg-core bert-cpp``` |
 | Embeddings | all-minilm-l6-v2 | ```docker run -ti -p 8080:8080 localai/localai:{{< version >}}-ffmpeg all-minilm-l6-v2``` |
 | Audio to Text | whisper-base | ```docker run -ti -p 8080:8080 localai/localai:{{< version >}}-ffmpeg-core whisper-base``` |
+| Text to Audio | rhasspy-voice-en-us-amy | ```docker run -ti -p 8080:8080 localai/localai:{{< version >}}-ffmpeg-core rhasspy-voice-en-us-amy``` |
+
 
 {{% /tab %}}
 {{% tab name="GPU (CUDA 11)" %}}
@@ -169,6 +171,7 @@ You can run `local-ai` directly with a model name, and it will download the mode
 | Embeddings | bert-cpp | ```docker run -ti -p 8080:8080 --gpus all localai/localai:{{< version >}}-cublas-cuda11-core bert-cpp``` |
 | Embeddings | all-minilm-l6-v2 | ```docker run -ti -p 8080:8080 --gpus all localai/localai:{{< version >}}-cublas-cuda11 all-minilm-l6-v2``` |
 | Audio to Text | whisper-base | ```docker run -ti -p 8080:8080 --gpus all localai/localai:{{< version >}}-cublas-cuda11-core whisper-base``` |
+| Text to Audio | rhasspy-voice-en-us-amy | ```docker run -ti -p 8080:8080 --gpus all localai/localai:{{< version >}}-cublas-cuda11-core rhasspy-voice-en-us-amy``` |
 
 {{% /tab %}}
 

embedded/models/bert-cpp.yaml

@@ -14,3 +14,10 @@ download_files:
   sha256: "a5a174d8772c8a569faf9f3136c441f2c3855b5bf35ed32274294219533feaad"
   uri: "https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin"
 
+usage: |
+    You can test this model with curl like this:
+
+    curl http://localhost:8080/embeddings -X POST -H "Content-Type: application/json" -d '{
+      "input": "Your text string goes here",
+      "model": "bert-cpp-minilm-v6"
+    }'