diff --git a/docs/getting_started.rst b/docs/getting_started.rst
index fd0babb55508d32ba7aac79a541e5e7066d26773..b0fa1d59e341ff7b096586df8a9cd5092e824561 100644
--- a/docs/getting_started.rst
+++ b/docs/getting_started.rst
@@ -20,13 +20,13 @@ the 'h5extract' command of km3pipe like so::
     yourself and let people know.
 
 
-Step 2: From h5 aanet files to DL files
----------------------------------------
-Produce DL files from the aanet h5 files using OrcaSong.
+Step 2: From h5 aanet files to h5 DL files
+------------------------------------------
+Produce DL h5 files from the aanet h5 files using OrcaSong.
 You can either produce images or graphs. See :ref:`orcasong_page` for
 instructions on how to do this.
 
-The resulting DL files can already be used as input for networks!
+The resulting DL h5 files can already be used as input for networks!
 
 Step 3: Concatenate
 -------------------
diff --git a/docs/orcasong.rst b/docs/orcasong.rst
index 7ad90195e6c844adbfb0fbbf8ffd1c7684761a2f..659e46ca88d0300b392d15dff667b7d3abc1e306 100644
--- a/docs/orcasong.rst
+++ b/docs/orcasong.rst
@@ -1,10 +1,10 @@
 .. _orcasong_page:
 
-Producing DL files from h5
-==========================
+Producing DL h5 files from aanet h5 files
+=========================================
 
-Describes how to use OrcaSong to produce files for Deep Learning
-from h5 files. These files can contain either images (for convolutional
+Describes how to use OrcaSong to produce h5 files for Deep Learning
+from aanet h5 files. These files can contain either images (for convolutional
 networks), or graphs (for Graph networks).
 
 .. contents:: :local: