diff --git a/native_client/deepspeech_compat.h b/native_client/deepspeech_compat.h
index 3709ae4f..57f3d16c 100644
--- a/native_client/deepspeech_compat.h
+++ b/native_client/deepspeech_compat.h
@@ -103,7 +103,7 @@ void DS_DiscardStream(StreamingState* aSctx)
  *
  * @param aCtx The ModelState pointer for the model to use.
  * @param aBuffer A 16-bit, mono raw audio signal at the appropriate
- *                sample rate.
+ *                sample rate (matching what the model was trained on).
  * @param aBufferSize The number of samples in the audio signal.
  * @param aSampleRate UNUSED, DEPRECATED.
  *
@@ -124,7 +124,7 @@ char* DS_SpeechToText(ModelState* aCtx,
  *
  * @param aCtx The ModelState pointer for the model to use.
  * @param aBuffer A 16-bit, mono raw audio signal at the appropriate
- *                sample rate.
+ *                sample rate (matching what the model was trained on).
  * @param aBufferSize The number of samples in the audio signal.
  * @param aSampleRate UNUSED, DEPRECATED.
  *
diff --git a/native_client/dotnet/DeepSpeechClient/DeepSpeech.cs b/native_client/dotnet/DeepSpeechClient/DeepSpeech.cs
index 84a7fa2b..25fcc109 100644
--- a/native_client/dotnet/DeepSpeechClient/DeepSpeech.cs
+++ b/native_client/dotnet/DeepSpeechClient/DeepSpeech.cs
@@ -148,7 +148,7 @@ namespace DeepSpeechClient
         /// <summary>
         /// Feeds audio samples to an ongoing streaming inference.
         /// </summary>
-        /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate.</param>
+        /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).</param>
         public unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize)
         {
             NativeImp.DS_FeedAudioContent(_streamingStatePP, aBuffer, aBufferSize);
@@ -229,7 +229,7 @@ namespace DeepSpeechClient
         /// <summary>
         /// Use the DeepSpeech model to perform Speech-To-Text.
         /// </summary>
-        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
+        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
         /// <param name="aBufferSize">The number of samples in the audio signal.</param>
         /// <returns>The STT result. The user is responsible for freeing the string.  Returns NULL on error.</returns>
         public unsafe string SpeechToText(short[] aBuffer, uint aBufferSize)
@@ -240,7 +240,7 @@ namespace DeepSpeechClient
         /// <summary>
         /// Use the DeepSpeech model to perform Speech-To-Text.
         /// </summary>
-        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
+        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
         /// <param name="aBufferSize">The number of samples in the audio signal.</param>
         /// <returns>The extended metadata. The user is responsible for freeing the struct.  Returns NULL on error.</returns>
         public unsafe Models.Metadata SpeechToTextWithMetadata(short[] aBuffer, uint aBufferSize)
diff --git a/native_client/dotnet/DeepSpeechClient/Interfaces/IDeepSpeech.cs b/native_client/dotnet/DeepSpeechClient/Interfaces/IDeepSpeech.cs
index da18a8ba..79af2964 100644
--- a/native_client/dotnet/DeepSpeechClient/Interfaces/IDeepSpeech.cs
+++ b/native_client/dotnet/DeepSpeechClient/Interfaces/IDeepSpeech.cs
@@ -40,7 +40,7 @@ namespace DeepSpeechClient.Interfaces
         /// <summary>
         /// Use the DeepSpeech model to perform Speech-To-Text.
         /// </summary>
-        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
+        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
         /// <param name="aBufferSize">The number of samples in the audio signal.</param>
         /// <returns>The STT result. The user is responsible for freeing the string.  Returns NULL on error.</returns>
         unsafe string SpeechToText(short[] aBuffer,
@@ -49,7 +49,7 @@ namespace DeepSpeechClient.Interfaces
         /// <summary>
         /// Use the DeepSpeech model to perform Speech-To-Text.
         /// </summary>
-        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
+        /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
         /// <param name="aBufferSize">The number of samples in the audio signal.</param>
         /// <returns>The extended metadata result. The user is responsible for freeing the struct.  Returns NULL on error.</returns>
         unsafe Metadata SpeechToTextWithMetadata(short[] aBuffer,
@@ -81,7 +81,7 @@ namespace DeepSpeechClient.Interfaces
         /// <summary>
         /// Feeds audio samples to an ongoing streaming inference.
         /// </summary>
-        /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate.</param>
+        /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).</param>
         unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize);
 
         /// <summary>
diff --git a/native_client/java/libdeepspeech/src/main/java/org/mozilla/deepspeech/libdeepspeech/DeepSpeechModel.java b/native_client/java/libdeepspeech/src/main/java/org/mozilla/deepspeech/libdeepspeech/DeepSpeechModel.java
index df0c047b..3a665c5e 100644
--- a/native_client/java/libdeepspeech/src/main/java/org/mozilla/deepspeech/libdeepspeech/DeepSpeechModel.java
+++ b/native_client/java/libdeepspeech/src/main/java/org/mozilla/deepspeech/libdeepspeech/DeepSpeechModel.java
@@ -57,7 +57,7 @@ public class DeepSpeechModel {
     * @brief Use the DeepSpeech model to perform Speech-To-Text.
     *
     * @param buffer A 16-bit, mono raw audio signal at the appropriate
-    *                sample rate.
+    *                sample rate (matching what the model was trained on).
     * @param buffer_size The number of samples in the audio signal.
     *
     * @return The STT result.
@@ -71,7 +71,7 @@ public class DeepSpeechModel {
     * about the results.
     *
     * @param buffer A 16-bit, mono raw audio signal at the appropriate
-    *                sample rate.
+    *                sample rate (matching what the model was trained on).
     * @param buffer_size The number of samples in the audio signal.
     *
     * @return Outputs a Metadata object of individual letters along with their timing information.
@@ -98,7 +98,7 @@ public class DeepSpeechModel {
     *
     * @param cctx A streaming state pointer returned by createStream().
     * @param buffer An array of 16-bit, mono raw audio samples at the
-    *                appropriate sample rate.
+    *                appropriate sample rate (matching what the model was trained on).
     * @param buffer_size The number of samples in @p buffer.
     */
     public void feedAudioContent(DeepSpeechStreamingState ctx, short[] buffer, int buffer_size) {
diff --git a/native_client/javascript/index.js b/native_client/javascript/index.js
index ab7f2e2d..f6446f4d 100644
--- a/native_client/javascript/index.js
+++ b/native_client/javascript/index.js
@@ -64,7 +64,7 @@ Model.prototype.enableDecoderWithLM = function() {
 /**
  * Use the DeepSpeech model to perform Speech-To-Text.
  *
- * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate.
+ * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
  * @param {number} aBufferSize The number of samples in the audio signal.
  *
  * @return {string} The STT result. Returns undefined on error.
@@ -78,7 +78,7 @@ Model.prototype.stt = function() {
  * Use the DeepSpeech model to perform Speech-To-Text and output metadata
  * about the results.
  *
- * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate.
+ * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
  * @param {number} aBufferSize The number of samples in the audio signal.
  *
  * @return {object} Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
@@ -111,7 +111,7 @@ Model.prototype.createStream = function() {
  *
  * @param {object} aSctx A streaming state returned by :js:func:`Model.setupStream`.
  * @param {buffer} aBuffer An array of 16-bit, mono raw audio samples at the
- *                 appropriate sample rate.
+ *                 appropriate sample rate (matching what the model was trained on).
  * @param {number} aBufferSize The number of samples in @param aBuffer.
  */
 Model.prototype.feedAudioContent = function() {
diff --git a/native_client/python/__init__.py b/native_client/python/__init__.py
index 14618ded..62ea1eb5 100644
--- a/native_client/python/__init__.py
+++ b/native_client/python/__init__.py
@@ -69,7 +69,7 @@ class Model(object):
         """
         Use the DeepSpeech model to perform Speech-To-Text.
 
-        :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate.
+        :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
         :type aBuffer: int array
 
         :param aBufferSize: The number of samples in the audio signal.
@@ -84,7 +84,7 @@ class Model(object):
         """
         Use the DeepSpeech model to perform Speech-To-Text and output metadata about the results.
 
-        :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate.
+        :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
         :type aBuffer: int array
 
         :param aBufferSize: The number of samples in the audio signal.
@@ -117,7 +117,7 @@ class Model(object):
         :param aSctx: A streaming state pointer returned by :func:`createStream()`.
         :type aSctx: object
 
-        :param aBuffer: An array of 16-bit, mono raw audio samples at the appropriate sample rate.
+        :param aBuffer: An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).
         :type aBuffer: int array
 
         :param aBufferSize: The number of samples in @p aBuffer.