From fe24b9d90b95012ac030f6919a766cbeab1b1ae3 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Wed, 19 Mar 2025 16:20:30 -0700
Subject: [PATCH] feat(azure/gpt_transformation.py): add azure audio model
 support

Closes https://github.com/BerriAI/litellm/issues/6305
---
 litellm/llms/azure/chat/gpt_transformation.py  |  2 ++
 litellm/llms/openai/chat/gpt_transformation.py |  1 +
 tests/llm_translation/test_optional_params.py  | 11 +++++++++++
 3 files changed, 14 insertions(+)

diff --git a/litellm/llms/azure/chat/gpt_transformation.py b/litellm/llms/azure/chat/gpt_transformation.py
index 7aa4fffab5..ee85517e66 100644
--- a/litellm/llms/azure/chat/gpt_transformation.py
+++ b/litellm/llms/azure/chat/gpt_transformation.py
@@ -99,6 +99,8 @@ class AzureOpenAIConfig(BaseConfig):
             "extra_headers",
             "parallel_tool_calls",
             "prediction",
+            "modalities",
+            "audio",
         ]
 
     def _is_response_format_supported_model(self, model: str) -> bool:
diff --git a/litellm/llms/openai/chat/gpt_transformation.py b/litellm/llms/openai/chat/gpt_transformation.py
index 8974a2a074..c765f97979 100644
--- a/litellm/llms/openai/chat/gpt_transformation.py
+++ b/litellm/llms/openai/chat/gpt_transformation.py
@@ -125,6 +125,7 @@ class OpenAIGPTConfig(BaseLLMModelInfo, BaseConfig):
             "max_retries",
             "extra_headers",
             "parallel_tool_calls",
+            "audio",
         ]  # works across all models
 
         model_specific_params = []
diff --git a/tests/llm_translation/test_optional_params.py b/tests/llm_translation/test_optional_params.py
index ad698e54c7..f59d434902 100644
--- a/tests/llm_translation/test_optional_params.py
+++ b/tests/llm_translation/test_optional_params.py
@@ -1368,3 +1368,14 @@ def test_bedrock_invoke_anthropic_max_tokens():
 
     assert "max_tokens_to_sample" not in optional_params
     assert optional_params["max_tokens"] == 1024
+
+
+def test_azure_modalities_param():
+    optional_params = get_optional_params(
+        model="chatgpt-v2",
+        custom_llm_provider="azure",
+        modalities=["text", "audio"],
+        audio={"type": "audio_input", "input": "test.wav"},
+    )
+    assert optional_params["modalities"] == ["text", "audio"]
+    assert optional_params["audio"] == {"type": "audio_input", "input": "test.wav"}