From 7ec44c042a03ab71448bb74fc15f88f74e4d34b4 Mon Sep 17 00:00:00 2001
From: richboyneedcash <273099414+richboyneedcash@users.noreply.github.com>
Date: Thu, 6 Aug 2026 11:37:55 +0800
Subject: [PATCH] fix: send whisper timestamp_granularities as bracketed array
 field

OpenAI's multipart transcription API expects array params as repeated
bracketed fields (timestamp_granularities[]=segment &
timestamp_granularities[]=word). LiteLLM stored the list under the bare
timestamp_granularities key, so OpenAI kept only the last value and a
combined ["segment", "word"] request silently returned just one
granularity (words OR segments, never both).

Rename the key to timestamp_granularities[] in
transform_audio_transcription_request so httpx encodes it as the repeated
bracketed fields OpenAI expects. This matches how the official
openai-python client serializes array form fields (array_format="brackets").

Fixes the multi-value case; single-value arrays already worked and
continue to.

Co-authored-by: TRAE CLI <noreply@bytedance.com>
---
 .../transcriptions/whisper_transformation.py  | 10 ++++
 .../test_whisper_transformation.py            | 50 +++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/litellm/llms/openai/transcriptions/whisper_transformation.py b/litellm/llms/openai/transcriptions/whisper_transformation.py
index 5e4bb19cbb3..70fd08290a2 100644
--- a/litellm/llms/openai/transcriptions/whisper_transformation.py
+++ b/litellm/llms/openai/transcriptions/whisper_transformation.py
@@ -109,6 +109,16 @@ class OpenAIWhisperAudioTranscriptionConfig(BaseAudioTranscriptionConfig):
         if "response_format" not in data:
             data["response_format"] = "verbose_json"  # ensures 'duration' is received - used for cost calculation
 
+        # OpenAI's multipart form API expects array params as repeated
+        # bracketed fields (`timestamp_granularities[]=segment` +
+        # `timestamp_granularities[]=word`). Sending the list under the bare
+        # `timestamp_granularities` key makes OpenAI keep only the last value,
+        # so a combined `["segment", "word"]` request silently returns just one
+        # granularity. Rename the key so the list is encoded as `[]` fields.
+        granularities = data.pop("timestamp_granularities", None)
+        if granularities is not None:
+            data["timestamp_granularities[]"] = granularities
+
         return AudioTranscriptionRequestData(
             data=data,
         )
diff --git a/tests/test_litellm/llms/openai/transcriptions/test_whisper_transformation.py b/tests/test_litellm/llms/openai/transcriptions/test_whisper_transformation.py
index 2dc24b1b313..ccc6aead6e2 100644
--- a/tests/test_litellm/llms/openai/transcriptions/test_whisper_transformation.py
+++ b/tests/test_litellm/llms/openai/transcriptions/test_whisper_transformation.py
@@ -48,6 +48,56 @@ class TestWhisperTransformRequestResponseFormat:
         assert data["response_format"] == "verbose_json"
 
 
+class TestWhisperTransformTimestampGranularities:
+    """
+    OpenAI's multipart form API expects array params as repeated bracketed
+    fields (``timestamp_granularities[]``). If the list is sent under the bare
+    ``timestamp_granularities`` key, OpenAI keeps only the last value, so a
+    combined ``["segment", "word"]`` request silently returns one granularity.
+    """
+
+    def _transform(self, optional_params: dict) -> dict:
+        config = OpenAIWhisperAudioTranscriptionConfig()
+        audio_file = io.BytesIO(b"fake audio")
+        audio_file.name = "test.wav"
+        result = config.transform_audio_transcription_request(
+            model="whisper-1",
+            audio_file=audio_file,
+            optional_params=optional_params,
+            litellm_params={},
+        )
+        return result.data
+
+    def test_multi_value_list_uses_bracketed_key(self):
+        """A multi-value list is sent under the bracketed key so both are honored."""
+        data = self._transform(
+            {
+                "response_format": "verbose_json",
+                "timestamp_granularities": ["segment", "word"],
+            }
+        )
+        assert data["timestamp_granularities[]"] == ["segment", "word"]
+        # The bare key must not be present, otherwise OpenAI drops all but the last.
+        assert "timestamp_granularities" not in data
+
+    def test_single_value_list_uses_bracketed_key(self):
+        """A single-value list is also sent under the bracketed key for consistency."""
+        data = self._transform(
+            {
+                "response_format": "verbose_json",
+                "timestamp_granularities": ["word"],
+            }
+        )
+        assert data["timestamp_granularities[]"] == ["word"]
+        assert "timestamp_granularities" not in data
+
+    def test_absent_granularities_not_added(self):
+        """When timestamp_granularities is not provided, no bracketed key is added."""
+        data = self._transform({"response_format": "verbose_json"})
+        assert "timestamp_granularities[]" not in data
+        assert "timestamp_granularities" not in data
+
+
 class TestWhisperTransformResponse:
     def _make_response(self, *, text: str, content_type: str, is_json: bool):
         mock = MagicMock()