support llama parse audio

py/llama_cloud_services/parse/types.py

@@ -112,7 +112,7 @@ class ChartItem(BaseModel):
 class Page(BaseModel):
     """A page of the document."""
 
-    page: int = Field(description="The page number.")
+    page: int = Field(default=0, description="The page number.")
     text: Optional[str] = Field(default=None, description="The text of the page.")
     md: Optional[str] = Field(default=None, description="The markdown of the page.")
     images: List[ImageItem] = Field(
@@ -153,6 +153,12 @@ class Page(BaseModel):
     noTextContent: bool = Field(
         default=False, description="Whether the page has no text content."
     )
+    isAudioTranscript: bool = Field(
+        default=False, description="Whether the page is an audio transcript."
+    )
+    durationInSeconds: Optional[float] = Field(
+        default=None, description="The duration of the audio transcript in seconds."
+    )
 
 
 class JobResult(BaseModel):

py/llama_parse/pyproject.toml

@@ -11,7 +11,7 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.56"
+version = "0.6.57"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"

py/pyproject.toml

@@ -18,7 +18,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.56"
+version = "0.6.57"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/tests/parse/test_llama_parse.py

@@ -202,3 +202,12 @@ async def test_get_result(markdown_parser: LlamaParse) -> None:
     result = await markdown_parser.aget_result(expected.job_id)
     assert result.job_id == expected.job_id
     assert len(result.pages) == len(expected.pages)
+
+
+@pytest.mark.asyncio
+async def test_parse_audio() -> None:
+    parser = LlamaParse()
+    filepath = "tests/test_files/hello_world.m4a"
+
+    result = await parser.aparse(filepath)
+    assert result.job_id is not None