diff --git a/README.md b/README.md
index c04f70d..c6cfcbf 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ Mimic 3 requires:
* Python 3.7 or higher
* The [Onnx runtime](https://onnxruntime.ai/)
-* [gruut](https://github.com/rhasspy/gruut) or [eSpeak-ng](https://github.com/espeak-ng/espeak-ng) (depending on the voice)
+* [gruut](https://github.com/rhasspy/gruut) or [eSpeak-ng](https://github.com/espeak-ng/espeak-ng) or [epitran](https://github.com/dmort27/epitran/) (depending on the voice)
## Installation
diff --git a/img/Mimic_color.svg b/img/Mimic_color.svg
new file mode 100644
index 0000000..e037c82
--- /dev/null
+++ b/img/Mimic_color.svg
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/mimic3-tts/README.md b/mimic3-tts/README.md
index 31c81b0..97411bf 100644
--- a/mimic3-tts/README.md
+++ b/mimic3-tts/README.md
@@ -285,6 +285,8 @@ Mimic 3 uses the [VITS](https://arxiv.org/abs/2106.06103), a "Conditional Variat
Our implementation is heavily based on [Jaehyeon Kim's PyTorch model](https://github.com/jaywalnut310/vits), with the addition of [Onnx runtime](https://onnxruntime.ai/) export for speed.
+
+
### Phoneme Ids
diff --git a/mimic3-tts/img/mimic3-architecture.png b/mimic3-tts/img/mimic3-architecture.png
new file mode 100644
index 0000000..209db1a
Binary files /dev/null and b/mimic3-tts/img/mimic3-architecture.png differ
diff --git a/mimic3-tts/img/mimic3-architecture.svg b/mimic3-tts/img/mimic3-architecture.svg
new file mode 100644
index 0000000..439e396
--- /dev/null
+++ b/mimic3-tts/img/mimic3-architecture.svg
@@ -0,0 +1,715 @@
+
+