diff --git a/tests/models/musicgen/test_modeling_musicgen.py b/tests/models/musicgen/test_modeling_musicgen.py
index 772285316140..02ab3b538c26 100644
--- a/tests/models/musicgen/test_modeling_musicgen.py
+++ b/tests/models/musicgen/test_modeling_musicgen.py
@@ -502,7 +502,7 @@ def prepare_config_and_inputs_for_common(self):
 class MusicgenTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin, unittest.TestCase):
     all_model_classes = (MusicgenForConditionalGeneration,) if is_torch_available() else ()
     greedy_sample_model_classes = (MusicgenForConditionalGeneration,) if is_torch_available() else ()
-    pipeline_model_mapping = {}
+    pipeline_model_mapping = {"text-to-audio": MusicgenForConditionalGeneration} if is_torch_available() else {}
     test_pruning = False  # training is not supported yet for MusicGen
     test_headmasking = False
     test_resize_embeddings = False
diff --git a/tests/models/vits/test_modeling_vits.py b/tests/models/vits/test_modeling_vits.py
index e767b036bea7..459a5587cfe8 100644
--- a/tests/models/vits/test_modeling_vits.py
+++ b/tests/models/vits/test_modeling_vits.py
@@ -40,6 +40,7 @@
     ids_tensor,
     random_attention_mask,
 )
+from ...test_pipeline_mixin import PipelineTesterMixin
 
 
 if is_torch_available():
@@ -153,8 +154,9 @@ def create_and_check_model_forward(self, config, inputs_dict):
 
 
 @require_torch
-class VitsModelTest(ModelTesterMixin, unittest.TestCase):
+class VitsModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     all_model_classes = (VitsModel,) if is_torch_available() else ()
+    pipeline_model_mapping = {"text-to-audio": VitsModel} if is_torch_available() else {}
     is_encoder_decoder = False
     test_pruning = False
     test_headmasking = False