content-core 1.6.0__py3-none-any.whl → 1.7.0__py3-none-any.whl

content_core/common/state.py

@@ -27,6 +27,14 @@ class ProcessSourceState(BaseModel):
         default=None,
         description="Override Docling output format: 'markdown', 'html', or 'json'",
     )
+    audio_provider: Optional[str] = Field(
+        default=None,
+        description="Override speech-to-text provider (e.g., 'openai', 'google')",
+    )
+    audio_model: Optional[str] = Field(
+        default=None,
+        description="Override speech-to-text model name (e.g., 'whisper-1', 'chirp')",
+    )
 
 
 class ProcessSourceInput(BaseModel):
@@ -36,6 +44,8 @@ class ProcessSourceInput(BaseModel):
     document_engine: Optional[str] = None
     url_engine: Optional[str] = None
     output_format: Optional[str] = None
+    audio_provider: Optional[str] = None
+    audio_model: Optional[str] = None
 
 
 class ProcessSourceOutput(BaseModel):

content_core/processors/audio.py

@@ -190,8 +190,39 @@ async def extract_audio_data(data: ProcessSourceState):
 
             # Transcribe audio files in parallel with concurrency limit
             from content_core.models import ModelFactory
+            from esperanto import AIFactory
+
+            # Determine which model to use based on state parameters
+            if data.audio_provider and data.audio_model:
+                # Custom model provided - create new instance
+                try:
+                    logger.info(
+                        f"Using custom audio model: {data.audio_provider}/{data.audio_model}"
+                    )
+                    speech_to_text_model = AIFactory.create_speech_to_text(
+                        data.audio_provider, data.audio_model
+                    )
+                except Exception as e:
+                    logger.error(
+                        f"Failed to create custom audio model '{data.audio_provider}/{data.audio_model}': {e}. "
+                        f"Check that the provider and model are supported by Esperanto. "
+                        f"Falling back to default model."
+                    )
+                    speech_to_text_model = ModelFactory.get_model("speech_to_text")
+            elif data.audio_provider or data.audio_model:
+                # Only one parameter provided - log warning and use default
+                missing = "audio_model" if data.audio_provider else "audio_provider"
+                provided = "audio_provider" if data.audio_provider else "audio_model"
+                logger.warning(
+                    f"{provided} provided without {missing}. "
+                    f"Both audio_provider and audio_model must be specified together. "
+                    f"Falling back to default model."
+                )
+                speech_to_text_model = ModelFactory.get_model("speech_to_text")
+            else:
+                # No custom parameters - use default (backward compatible)
+                speech_to_text_model = ModelFactory.get_model("speech_to_text")
 
-            speech_to_text_model = ModelFactory.get_model("speech_to_text")
             concurrency = get_audio_concurrency()
             semaphore = asyncio.Semaphore(concurrency)
 

content_core/templated_message.py

@@ -2,7 +2,6 @@ from typing import Dict, Optional, Union
 
 from ai_prompter import Prompter
 from esperanto import LanguageModel
-from esperanto.common_types import Message
 from pydantic import BaseModel, Field
 
 from content_core.models import ModelFactory

{content_core-1.6.0.dist-info → content_core-1.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.6.0
+Version: 1.7.0
 Summary: Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
@@ -263,6 +263,14 @@ cleaned_text = await cc.clean("...messy text with [brackets] and extra spaces...
 
 # Summarize content with optional context
 summary = await cc.summarize_content("long article text", context="explain to a child")
+
+# Extract audio with custom speech-to-text model
+from content_core.common import ProcessSourceInput
+result = await cc.extract(ProcessSourceInput(
+    file_path="interview.mp3",
+    audio_provider="openai",
+    audio_model="whisper-1"
+))
 ```
 
 ## Documentation

{content_core-1.6.0.dist-info → content_core-1.7.0.dist-info}/RECORD

@@ -5,10 +5,10 @@ content_core/logging.py,sha256=oeRdWKknEolptopxF1IvnEGEc0ZUw45QXYUEZ71GcdY,438
 content_core/models.py,sha256=Kt6tWdAX87eQ2tL6eTwcHU7_NIRnN4exP4RzV2WrMig,881
 content_core/models_config.yaml,sha256=Yr-GS94ffxnkaWojUfpErUMM7m_MShsYjR6QuDjMzwo,444
 content_core/py.typed,sha256=pLuU3XTTeVpXo4UomOjcvAIQqOrzIotlWlJ3KFo2lxQ,154
-content_core/templated_message.py,sha256=jsjGqD-zf__pV4P0eo9cffTK2C90-VggL64qNYejFo0,1615
+content_core/templated_message.py,sha256=F4ysbVUWG1V3-pT8NYbCzP5mJN_qRYtiWPa9gxjB9v0,1572
 content_core/common/__init__.py,sha256=SjDp-0QRjX9PMubyTjv77_GrUqm6eC4gBuXr593JVK4,525
 content_core/common/exceptions.py,sha256=NpYedVbckIq4kP2wek7bicMVgGGn0fkhCvid5cIxfy4,1304
-content_core/common/state.py,sha256=K5jsDg4l2GSaoGyFYzdd1GW14vLaAxdxes8vUrPNVkE,1622
+content_core/common/state.py,sha256=Xxxtdi650x4zkNX3yXA9Jx79GAzud7Vu-I7eNEjHlhI,2010
 content_core/common/types.py,sha256=DOQFW5ySHELc_mZU6G_7PUy1kmnP4aU4IpMyyXDQcBE,177
 content_core/common/utils.py,sha256=0o4jovPEw_6wu7EcPPbDNZskbhhfLUBJBvRmp0Yc4R4,1182
 content_core/content/__init__.py,sha256=7IxfLTUHKyHjoT4MfWM2PX2J3QBeYcuERzE9vFeFiQM,230
@@ -24,7 +24,7 @@ content_core/mcp/__init__.py,sha256=KNZYH4F9AoW1Orw1BtO3n92Cn-127hI7iF9gnGadueU,
 content_core/mcp/server.py,sha256=ql0uXHkIbZlHQUhUQ4CaRnj19xT6t8ErydWntFgmtUg,7021
 content_core/notebooks/run.ipynb,sha256=8gbFln9WLrli_qWJB8SKQKcSNbAv25DvN5Cu4EAAeBQ,370952
 content_core/notebooks/urls.ipynb,sha256=gSmiSzmbol_Li36w8tpUsy5QgRbrnBx94Ry2zHwMvwY,7107
-content_core/processors/audio.py,sha256=CYwoTDPsVUDALHuz_EHcnjVfsKF8XjQmvmX8c-OmMNU,8462
+content_core/processors/audio.py,sha256=h4aPff8WjDklE2iCviuAEEAYJTTxmWh9nOgMYJHWzmM,10202
 content_core/processors/docling.py,sha256=lf_NHh255gn4d2EymJYqyH2QiAgQDiJCY3t6Ne7R9rU,2507
 content_core/processors/office.py,sha256=DXkfmjqUhmhP6rJaO5Z5Y9sv-iK0zaPZ3waynFIPtsk,12153
 content_core/processors/pdf.py,sha256=TTDhfV2INtXumFDjLJFNMRfpbJ_tqwIcSBDzuThKxJI,10617
@@ -36,8 +36,8 @@ content_core/tools/__init__.py,sha256=DuJmd7fE-NpDvLP8IW1XY5MUkAQcdks52rn2jk4N8j
 content_core/tools/cleanup.py,sha256=5IdKedsFyRQMdYzgFSKtsfyxJldbroXQXHesHICNENI,523
 content_core/tools/extract.py,sha256=-r2_jsuMMXyXxGVqWhh1ilNPo_UMYAbw3Pkp1FzPy5g,577
 content_core/tools/summarize.py,sha256=DPfeglLWB08q8SvHrsKpOKZ35XjduUDs2J02ISwjdj0,596
-content_core-1.6.0.dist-info/METADATA,sha256=bBxEINm9h2ppJIia11flDRDH7UshzamVrHKHGxHrmjs,21963
-content_core-1.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-content_core-1.6.0.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
-content_core-1.6.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
-content_core-1.6.0.dist-info/RECORD,,
+content_core-1.7.0.dist-info/METADATA,sha256=l3oDAdfN_gMFfOgHz3fELrjSxUXq8AKRKbC5uVF6mzM,22201
+content_core-1.7.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+content_core-1.7.0.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
+content_core-1.7.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
+content_core-1.7.0.dist-info/RECORD,,