Fix Sphinx docstring RST formatting warnings

Replace Markdown code blocks with RST syntax in genesys.py, fix
deprecated directive transitions in nvidia and summarization modules,
remove stray bullet prefix in whisper arg docs, restructure code block
in turn completion mixin, and add deepgram mock to Sphinx conf.

docs/api/conf.py

@@ -97,6 +97,8 @@ autodoc_mock_imports = [
     "fastapi.middleware",
     "fastapi.responses",
     "uvicorn",
+    # Deepgram dependencies
+    "deepgram",
 ]
 
 # HTML output settings

src/pipecat/serializers/genesys.py

@@ -95,8 +95,8 @@ class GenesysAudioHookSerializer(FrameSerializer):
     - Text WebSocket frames for JSON control messages
     - Binary WebSocket frames for audio data
 
-    Example usage:
-        ```python
+    Example usage::
+
         serializer = GenesysAudioHookSerializer(
             params=GenesysAudioHookSerializer.InputParams(
                 channel=AudioHookChannel.EXTERNAL,
@@ -122,7 +122,6 @@ class GenesysAudioHookSerializer(FrameSerializer):
 
         # Set output variables to return to Architect
         serializer.set_output_variables({"intent": "billing", "resolved": True})
-        ```
 
     Attributes:
         PROTOCOL_VERSION: The AudioHook protocol version (currently "2").
@@ -246,8 +245,8 @@ class GenesysAudioHookSerializer(FrameSerializer):
         Args:
             variables: Dictionary of custom variables to send to Genesys.
 
-        Example:
-            ```python
+        Example::
+
             # During the conversation, collect data and set it
             serializer.set_output_variables({
                 "intent": "billing_inquiry",
@@ -255,7 +254,6 @@ class GenesysAudioHookSerializer(FrameSerializer):
                 "summary": "Customer asked about their bill",
                 "transfer_to": "billing_queue"
             })
-            ```
         """
         self._output_variables = variables
         logger.debug(f"Output variables set: {variables}")
@@ -413,8 +411,8 @@ class GenesysAudioHookSerializer(FrameSerializer):
         Returns:
             Dictionary of the closed response message.
 
-        Example:
-            ```python
+        Example::
+
             # Pass custom data back to Genesys
             serializer.create_closed_response(
                 output_variables={
@@ -423,7 +421,6 @@ class GenesysAudioHookSerializer(FrameSerializer):
                     "summary": "Customer asked about their bill"
                 }
             )
-            ```
         """
         parameters: Optional[Dict[str, Any]] = None
 

src/pipecat/services/google/tts.py

@@ -520,8 +520,7 @@ class GoogleTTSSettings(TTSSettings):
     speaking_rate: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
 
 
-#: .. deprecated:: 0.0.105
-#:     Use ``GoogleTTSService.Settings`` instead.
+#: *Deprecated since 0.0.105:* Use ``GoogleTTSService.Settings`` instead.
 GoogleStreamTTSSettings = GoogleTTSSettings
 
 

src/pipecat/services/nvidia/stt.py

@@ -269,7 +269,9 @@ class NvidiaSTTService(STTService):
 
         .. deprecated:: 0.0.104
             Model cannot be changed after initialization for NVIDIA Riva streaming STT.
-            Set model and function id in the constructor instead, e.g.::
+            Set model and function id in the constructor instead.
+
+            Example::
 
                 NvidiaSTTService(
                     api_key=...,

src/pipecat/services/nvidia/tts.py

@@ -163,7 +163,9 @@ class NvidiaTTSService(TTSService):
 
         .. deprecated:: 0.0.104
             Model cannot be changed after initialization for NVIDIA Riva TTS.
-            Set model and function id in the constructor instead, e.g.::
+            Set model and function id in the constructor instead.
+
+            Example::
 
                 NvidiaTTSService(
                     api_key=...,

src/pipecat/services/whisper/base_stt.py

@@ -168,7 +168,7 @@ class BaseWhisperSTTService(SegmentedSTTService):
             include_prob_metrics: If True, enables probability metrics in API response.
                 Each service implements this differently (see child classes).
                 Defaults to False.
-            push_empty_transcripts: - If true, allow empty `TranscriptionFrame` frames to be
+            push_empty_transcripts: If true, allow empty `TranscriptionFrame` frames to be
                 pushed downstream instead of discarding them. This is intended for situations
                 where VAD fires even though the user did not speak. In these cases, it is
                 useful to know that nothing was transcribed so that the agent can resume

src/pipecat/turns/user_turn_completion_mixin.py

@@ -191,9 +191,7 @@ class UserTurnCompletionLLMServiceMixin:
     When incomplete timeouts expire, the mixin automatically prompts the LLM
     with a contextual follow-up message to re-engage the user.
 
-    Usage:
-        The LLM service controls when to use turn completion by calling
-        _push_turn_text instead of push_frame:
+    Usage example::
 
         # With turn completion:
         if self._filter_incomplete_user_turns:
@@ -201,7 +199,10 @@ class UserTurnCompletionLLMServiceMixin:
         else:
             await self.push_frame(LLMTextFrame(chunk.text))
 
-    The mixin requires that the base class has a `push_frame` method compatible
+    The LLM service controls when to use turn completion by calling
+    ``_push_turn_text`` instead of ``push_frame``.
+
+    The mixin requires that the base class has a ``push_frame`` method compatible
     with FrameProcessor's signature.
     """
 

src/pipecat/utils/context/llm_context_summarization.py

@@ -168,7 +168,9 @@ class LLMContextSummarizationConfig:
 
     .. deprecated:: 0.0.104
         Use :class:`LLMAutoContextSummarizationConfig` with a nested
-        :class:`LLMContextSummaryConfig` instead::
+        :class:`LLMContextSummaryConfig` instead.
+
+        Example::
 
             LLMAutoContextSummarizationConfig(
                 max_context_tokens=8000,