Update README.md

diff --git a/examples/talk/README.md b/examples/talk/README.md
index 6923e890f759aed18b052e74a8ac56f871c8c5f6..316a2ae34b04d50d4c7569a6a81182cb25cc4156 100644 (file)
--- a/examples/talk/README.md
+++ b/examples/talk/README.md
@@ -24,6 +24,8 @@ make talk
 ./talk -p Santa\r
 ```\r
 \r
+## GPT-2\r
+\r
 To run this, you will need a ggml GPT-2 model: [instructions](https://github.com/ggerganov/ggml/tree/master/examples/gpt-2#downloading-and-converting-the-original-models)\r
 \r
 Alternatively, you can simply download the smallest ggml GPT-2 117M model (240 MB) like this:\r
@@ -31,3 +33,9 @@ Alternatively, you can simply download the smallest ggml GPT-2 117M model (240 M
 ```\r
 wget --quiet --show-progress -O models/ggml-gpt-2-117M.bin https://ggml.ggerganov.com/ggml-model-gpt-2-117M.bin\r
 ```\r
+\r
+## TTS\r
+\r
+For best experience, this example needs a TTS tool to convert the generated text responses to voice.\r
+You can use any TTS engine that you would like - simply edit the [speak.sh](speak.sh) script to your needs.\r
+By default, it is configured to use `espeak`, but you can use whatever you wish.\r