diff --git a/google/cloud/speech/v2/cloud_speech.proto b/google/cloud/speech/v2/cloud_speech.proto
index a8f23239e0c49..3e7b979a0e69a 100644
--- a/google/cloud/speech/v2/cloud_speech.proto
+++ b/google/cloud/speech/v2/cloud_speech.proto
@@ -865,6 +865,13 @@ message TranscriptNormalization {
   repeated Entry entries = 1;
 }
 
+// Translation configuration. Use to translate the given audio into text for the
+// desired language.
+message TranslationConfig {
+  // Required. The language code to translate to.
+  string target_language = 1 [(google.api.field_behavior) = REQUIRED];
+}
+
 // Provides "hints" to the speech recognizer to favor specific words and phrases
 // in the results. PhraseSets can be specified as an inline resource, or a
 // reference to an existing PhraseSet resource.
@@ -943,6 +950,11 @@ message RecognitionConfig {
   // and final transcripts.
   TranscriptNormalization transcript_normalization = 11
       [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Optional configuration used to automatically run translation on
+  // the given audio to the desired language for supported models.
+  TranslationConfig translation_config = 15
+      [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Request message for the