Rename *-local-vad.py example variants to *-locally-driven-turns.py

The "-local-vad" suffix was ambiguous now that local VAD has two
meanings in the realtime context: supplementary user-turn frames
broadcast alongside server-driven turns (commented-out opt-in in the
base examples), vs. local turn detection driving the conversation
end-to-end (server-side turn detection disabled, what these variant
files actually demonstrate). The new "-locally-driven-turns" suffix
matches the latter intent unambiguously.

Renames:

  realtime-openai-local-vad.py       → realtime-openai-locally-driven-turns.py
  realtime-gemini-live-local-vad.py  → realtime-gemini-live-locally-driven-turns.py
  realtime-grok-local-vad.py         → realtime-grok-locally-driven-turns.py
  realtime-inworld-local-vad.py      → realtime-inworld-locally-driven-turns.py

Plus the matching changelog fragments. Service docstrings and base
examples that referenced the old filenames now point at the new ones.

changelog/+realtime-grok-local-vad-example.added.md

@@ -1 +0,0 @@
-- Added `examples/realtime/realtime-grok-local-vad.py`, a variant of the base Grok Realtime example that disables Grok's server-side turn detection (`turn_detection=None`, manual mode) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Mirrors the OpenAI Realtime local-VAD variant. Server-emitted turn frames are preferred when available.

changelog/+realtime-grok-locally-driven-turns-example.added.md

@@ -0,0 +1 @@
+- Added `examples/realtime/realtime-grok-locally-driven-turns.py`, a variant of the base Grok Realtime example that disables Grok's server-side turn detection (`turn_detection=None`, manual mode) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Mirrors the OpenAI Realtime locally-driven-turns variant. Server-emitted turn frames are preferred when available.

changelog/+realtime-inworld-local-vad-example.added.md

@@ -1 +0,0 @@
-- Added `examples/realtime/realtime-inworld-local-vad.py`, a variant of the base Inworld Realtime example that disables Inworld's server-side turn detection (`turn_detection=None`, manual mode) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Mirrors the OpenAI Realtime and Grok Realtime local-VAD variants. Server-emitted turn frames are preferred when available.

changelog/+realtime-inworld-locally-driven-turns-example.added.md

@@ -0,0 +1 @@
+- Added `examples/realtime/realtime-inworld-locally-driven-turns.py`, a variant of the base Inworld Realtime example that disables Inworld's server-side turn detection (`turn_detection=None`, manual mode) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Mirrors the OpenAI Realtime and Grok Realtime locally-driven-turns variants. Server-emitted turn frames are preferred when available.

changelog/+realtime-openai-local-vad-example.added.md

@@ -1 +0,0 @@
-- Added `examples/realtime/realtime-openai-local-vad.py`, a variant of the base OpenAI Realtime example that disables OpenAI's server-side turn detection (`turn_detection=False`) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Use this variant if you need a turn analyzer like `LocalSmartTurnV3` to decide when the user is done speaking, or if you need `UserStartedSpeakingFrame` / `UserStoppedSpeakingFrame` to fire from the same source as `InterruptionFrame`. Server-emitted turn frames are preferred when available.

changelog/+realtime-openai-locally-driven-turns-example.added.md

@@ -0,0 +1 @@
+- Added `examples/realtime/realtime-openai-locally-driven-turns.py`, a variant of the base OpenAI Realtime example that disables OpenAI's server-side turn detection (`turn_detection=False`) and instead drives turn boundaries locally with `SileroVADAnalyzer` wired into the user aggregator. Use this variant if you need a turn analyzer like `LocalSmartTurnV3` to decide when the user is done speaking, or if you need `UserStartedSpeakingFrame` / `UserStoppedSpeakingFrame` to fire from the same source as `InterruptionFrame`. Server-emitted turn frames are preferred when available.

examples/realtime/realtime-gemini-live.py

@@ -147,7 +147,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # decisions and can desynchronize in subtle ways.
     #
     # For local VAD driving the conversation (server VAD disabled), see
-    # `realtime-gemini-live-local-vad.py` instead.
+    # `realtime-gemini-live-locally-driven-turns.py` instead.
     #
     # from pipecat.audio.vad.silero import SileroVADAnalyzer
     # from pipecat.processors.aggregators.llm_response_universal import (

examples/realtime/realtime-openai.py

@@ -190,8 +190,8 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         # own UserStarted/StoppedSpeakingFrame from server VAD events, so
         # local VAD on the aggregator is unnecessary. realtime_service_mode
         # decouples context writes from turn frames and transcript-bound
-        # turn-end. See `realtime-openai-local-vad.py` for the variant
-        # that disables server VAD and drives turn detection locally.
+        # turn-end. See `realtime-openai-locally-driven-turns.py` for the
+        # variant that disables server VAD and drives turn detection locally.
         realtime_service_mode=RealtimeServiceModeConfig(),
     )
 

src/pipecat/services/google/gemini_live/llm.py

@@ -370,7 +370,7 @@ class GeminiLiveLLMService(LLMService[GeminiLLMAdapter]):
     detector — won't activate with the default server-VAD-only setup. Pair
     with ``LLMContextAggregatorPair(..., realtime_service_mode=RealtimeServiceModeConfig())``
     so context writes are correct anyway. To produce the turn frames
-    locally, see ``examples/realtime/realtime-gemini-live-local-vad.py``;
+    locally, see ``examples/realtime/realtime-gemini-live-locally-driven-turns.py``;
     note that locally-generated turn boundaries are a heuristic and may
     not match Gemini Live's server-side turn decisions.
     """

src/pipecat/services/inworld/realtime/llm.py

@@ -209,7 +209,7 @@ class InworldRealtimeLLMService(LLMService[InworldRealtimeLLMAdapter]):
     service, disable Inworld's server-side turn detection first via
     ``turn_detection=None`` (manual mode); otherwise both sources
     broadcast duplicate user-turn frames. See
-    ``examples/realtime/realtime-inworld-local-vad.py``.
+    ``examples/realtime/realtime-inworld-locally-driven-turns.py``.
 
     Example::
 

src/pipecat/services/openai/realtime/llm.py

@@ -218,7 +218,7 @@ class OpenAIRealtimeLLMService(LLMService[OpenAIRealtimeLLMAdapter]):
     top of this service, disable OpenAI's server-side turn detection
     first (``turn_detection=False``); otherwise both sources broadcast
     duplicate user-turn frames. See
-    ``examples/realtime/realtime-openai-local-vad.py``.
+    ``examples/realtime/realtime-openai-locally-driven-turns.py``.
     """
 
     Settings = OpenAIRealtimeLLMSettings

src/pipecat/services/xai/realtime/llm.py

@@ -204,7 +204,7 @@ class GrokRealtimeLLMService(LLMService[GrokRealtimeLLMAdapter]):
     service, disable Grok's server-side turn detection first via
     ``turn_detection=None`` (manual mode); otherwise both sources
     broadcast duplicate user-turn frames. See
-    ``examples/realtime/realtime-grok-local-vad.py``.
+    ``examples/realtime/realtime-grok-locally-driven-turns.py``.
     """
 
     Settings = GrokRealtimeLLMSettings