diff --git a/docs/source/recipes/TTS/ljspeech/vits.rst b/docs/source/recipes/TTS/ljspeech/vits.rst
index 244ea992c..d08aa0f47 100644
--- a/docs/source/recipes/TTS/ljspeech/vits.rst
+++ b/docs/source/recipes/TTS/ljspeech/vits.rst
@@ -4,6 +4,10 @@ VITS
 This tutorial shows you how to train an VITS model
 with the `LJSpeech <https://keithito.com/LJ-Speech-Dataset/>`_ dataset.
 
+.. note::
+  
+   TTS related recipes require packages in ``requirements-tts.txt``.
+
 .. note::
 
    The VITS paper: `Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech <https://arxiv.org/pdf/2106.06103.pdf>`_
@@ -27,6 +31,12 @@ To run stage 1 to stage 5, use
 Build Monotonic Alignment Search
 --------------------------------
 
+.. code-block:: bash
+
+  $ ./prepare.sh --stage -1 --stop_stage -1
+
+or
+
 .. code-block:: bash
 
   $ cd vits/monotonic_align
diff --git a/docs/source/recipes/TTS/vctk/vits.rst b/docs/source/recipes/TTS/vctk/vits.rst
index 99bd3ab83..34024a5ea 100644
--- a/docs/source/recipes/TTS/vctk/vits.rst
+++ b/docs/source/recipes/TTS/vctk/vits.rst
@@ -4,6 +4,10 @@ VITS
 This tutorial shows you how to train an VITS model
 with the `VCTK <https://datashare.ed.ac.uk/handle/10283/3443>`_ dataset.
 
+.. note::
+  
+   TTS related recipes require packages in ``requirements-tts.txt``.
+
 .. note::
 
    The VITS paper: `Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech <https://arxiv.org/pdf/2106.06103.pdf>`_
@@ -31,7 +35,7 @@ To build the monotonic alignment search, use the following commands:
 
 .. code-block:: bash
 
-  $ ./prepare.sh --stage 7 --stop_stage 7
+  $ ./prepare.sh --stage -1 --stop_stage -1
 
 or
 
diff --git a/egs/ljspeech/TTS/prepare.sh b/egs/ljspeech/TTS/prepare.sh
index 8ee40896e..ed0a07f5e 100755
--- a/egs/ljspeech/TTS/prepare.sh
+++ b/egs/ljspeech/TTS/prepare.sh
@@ -5,8 +5,7 @@ export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
 
 set -eou pipefail
 
-nj=1
-stage=-1
+stage=0
 stop_stage=100
 
 dl_dir=$PWD/download
@@ -25,6 +24,17 @@ log() {
 
 log "dl_dir: $dl_dir"
 
+if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
+  log "Stage -1: build monotonic_align lib"
+  if [ ! -d vits/monotonic_align/build ]; then
+    cd vits/monotonic_align
+    python setup.py build_ext --inplace
+    cd ../../
+  else 
+    log "monotonic_align lib already built"
+  fi
+fi
+
 if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
   log "Stage 0: Download data"
 
@@ -113,5 +123,3 @@ if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
       --tokens data/tokens.txt
   fi
 fi
-
-
diff --git a/egs/vctk/TTS/prepare.sh b/egs/vctk/TTS/prepare.sh
index b6c05aa5c..87150ad31 100755
--- a/egs/vctk/TTS/prepare.sh
+++ b/egs/vctk/TTS/prepare.sh
@@ -5,8 +5,7 @@ export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
 
 set -eou pipefail
 
-nj=1
-stage=-1
+stage=0
 stop_stage=100
 
 dl_dir=$PWD/download
@@ -25,6 +24,17 @@ log() {
 
 log "dl_dir: $dl_dir"
 
+if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
+  log "Stage -1: build monotonic_align lib"
+  if [ ! -d vits/monotonic_align/build ]; then
+    cd vits/monotonic_align
+    python setup.py build_ext --inplace
+    cd ../../
+  else 
+    log "monotonic_align lib already built"
+  fi
+fi
+
 if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
   log "Stage 0: Download data"
 
@@ -119,14 +129,3 @@ if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
       | sort | uniq > data/speakers.txt
   fi
 fi
-
-if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
-  log "Stage 7: build monotonic_align lib"
-  if [ ! -d vits/monotonic_align/build ]; then
-    cd vits/monotonic_align
-    python setup.py build_ext --inplace
-    cd ../../
-  else 
-    log "monotonic_align lib already built"
-  fi
-fi
diff --git a/requirements_tts.txt b/requirements-tts.txt
similarity index 100%
rename from requirements_tts.txt
rename to requirements-tts.txt