Merge pull request #2389 from pipecat-ai/aleix/pipecat-0.0.78

update CHANGELOG for 0.0.78

.github/workflows/python-compatibility.yaml

@@ -0,0 +1,61 @@
+name: Python Compatibility Test
+
+on:
+  push:
+    branches: [main, develop]
+    paths: ['pyproject.toml']
+  pull_request:
+    branches: [main, develop]
+    paths: ['pyproject.toml']
+
+jobs:
+  test-compatibility:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
+
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y \
+            portaudio19-dev \
+            libcairo2-dev \
+            libgirepository1.0-dev \
+            pkg-config
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: 'latest'
+
+      - name: Set up Python ${{ matrix.python-version }}
+        run: |
+          uv python install ${{ matrix.python-version }}
+          uv python pin ${{ matrix.python-version }}
+
+      - name: Test uv sync with all extras (Python < 3.13)
+        if: "!startsWith(matrix.python-version, '3.13.')"
+        run: |
+          uv sync --group dev --all-extras --no-extra krisp
+
+      - name: Test uv sync without PyTorch extras (Python 3.13+)
+        if: startsWith(matrix.python-version, '3.13.')
+        run: |
+          uv sync --group dev --all-extras \
+            --no-extra krisp \
+            --no-extra ultravox \
+            --no-extra local-smart-turn \
+            --no-extra moondream \
+            --no-extra mlx-whisper
+
+      - name: Verify installation
+        run: |
+          uv run python --version
+          uv run python -c "import pipecat; print('✅ Pipecat imports successfully')"

CHANGELOG.md

@@ -5,13 +5,20 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.0.78] - 2025-08-07
 
 ### Added
 
+- Added `enable_emulated_vad_interruptions` to `LLMUserAggregatorParams`.
+  When user speech is emulated (e.g. when a transcription is received but
+  VAD doesn't detect speech), this parameter controls whether the emulated
+  speech can interrupt the bot. Default is False (emulated speech is ignored
+  while the bot is speaking).
+
 - Added new `handle_sigint` and `handle_sigterm` to `RunnerArguments`. This
   allows applications to know what settings they should use for the environment
-  they are running on.
+  they are running on. Also, added `pipeline_idle_timeout_secs` to be able to
+  control the `PipelineTask` idle timeout.
 
 - Added `processor` field to `ErrorFrame` to indicate `FrameProcessor` that
   generated the error.
@@ -46,6 +53,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added Chinese, Japanese, Korean word timestamp support to
   `CartesiaTTSService`.
 
+- Added `region` parameter to `GladiaSTTService`. Accepted values: eu-west (default), us-west.
+
 ### Changed
 
 - System frames are now queued. Before, system frames could be generated from
@@ -77,8 +86,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - The development runner now strips any provided protocol (e.g. https://) from
   the proxy address and issues a warning. It also strips trailing `/`.
 
+### Deprecated
+
+- In the `pipecat.runner.daily`, the `configure_with_args()` function is
+  deprecated. Use the `configure()` function instead.
+
+- The development runner's `/connect` endpoint is deprecated and will be
+  removed in a future version. Use the `/start` endpoint in its place. In the
+  meantime, both endpoints work and deliver equivalent functionality.
+
 ### Fixed
 
+- Fixed a `DailyTransport` issue that would result in an unhandled
+  `concurrent.futures.CancelledError` when a future is cancelled.
+
+- Fixed a `RivaSTTService` issue that would result in an unhandled
+  `concurrent.futures.CancelledError` when a future is cancelled when reading
+  from the audio chunks from the incoming audio stream.
+
+- Fixed an issue in the `BaseOutputTransport`, mainly reproducible with
+  `FastAPIWebsocketOutputTransport` when the audio mixer was enabled, where the
+  loop could consume 100% CPU by continuously returning without delay, preventing
+  other asyncio tasks (such as cancellation or shutdown signals) from being
+  processed.
+
 - Fixed an issue where `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`
   were not emitted when using `TavusVideoService` or `HeyGenVideoService`.
 
@@ -98,14 +129,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue in `TaskObserver` (a proxy to all observers) that was degrading
   global performance.
 
-### Deprecated
+### Other
 
-- In the `pipecat.runner.daily`, the `configure_with_args()` function is
-  deprecated. Use the `configure()` function instead.
-
-- The development runner's `/connect` endpoint is deprecated and will be
-  removed in a future version. Use the `/start` endpoint in its place. In the
-  meantime, both endpoints work and deliver equivalent functionality.
+- Added `07aa-interruptible-soniox.py`, `07ab-interruptible-inworld-http.py`,
+  `07ac-interruptible-asyncai.py` and `07ac-interruptible-asyncai-http.py`
+  release evals.
 
 ## [0.0.77] - 2025-07-31
 

README.md

@@ -112,6 +112,12 @@ You can get started with Pipecat running on your local machine, then move your a
 
 ## 🛠️ Contributing to the framework
 
+### Prerequisites
+
+**Python Version:** 3.10+
+
+### Setup Steps
+
 1. Clone the repository and navigate to it:
 
    ```bash
@@ -131,6 +137,18 @@ You can get started with Pipecat running on your local machine, then move your a
    uv run pre-commit install
    ```
 
+### Python 3.13+ Note
+
+Some features require PyTorch (not yet available on Python 3.13+):
+
+- `ultravox`, `local-smart-turn`, `moondream`, `mlx-whisper`
+
+**For full compatibility:** Use Python 3.12
+
+```bash
+uv python pin 3.12 && uv sync --group dev --all-extras --no-extra krisp
+```
+
 ### Running tests
 
 To run all tests, from the root directory:

env.example

@@ -44,6 +44,7 @@ FIREWORKS_API_KEY=...
 
 # Gladia
 GLADIA_API_KEY=...
+GLADIA_REGION=...
 
 # Google
 GOOGLE_API_KEY=...
@@ -135,4 +136,4 @@ SAMBANOVA_API_KEY=...
 SENTRY_DSN=...
 
 # Heygen
-HEYGEN_API_KEY=...
+HEYGEN_API_KEY=...

examples/foundational/01-say-one-thing-piper.py

@@ -43,7 +43,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
         )
 
-        task = PipelineTask(Pipeline([tts, transport.output()]))
+        task = PipelineTask(
+            Pipeline([tts, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
         # Register an event handler so we can play the audio when the client joins
         @transport.event_handler("on_client_connected")

examples/foundational/01-say-one-thing-rime.py

@@ -44,7 +44,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             aiohttp_session=session,
         )
 
-        task = PipelineTask(Pipeline([tts, transport.output()]))
+        task = PipelineTask(
+            Pipeline([tts, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
         # Register an event handler so we can play the audio when the client joins
         @transport.event_handler("on_client_connected")

examples/foundational/01-say-one-thing.py

@@ -41,7 +41,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    task = PipelineTask(Pipeline([tts, transport.output()]))
+    task = PipelineTask(
+        Pipeline([tts, transport.output()]),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     # Register an event handler so we can play the audio when the client joins
     @transport.event_handler("on_client_connected")

examples/foundational/01c-fastpitch.py

@@ -38,7 +38,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-    task = PipelineTask(Pipeline([tts, transport.output()]))
+    task = PipelineTask(
+        Pipeline([tts, transport.output()]),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     # Register an event handler so we can play the audio when the client joins
     @transport.event_handler("on_client_connected")

examples/foundational/02-llm-say-one-thing.py

@@ -51,7 +51,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         }
     ]
 
-    task = PipelineTask(Pipeline([llm, tts, transport.output()]))
+    task = PipelineTask(
+        Pipeline([llm, tts, transport.output()]),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     # Register an event handler so we can play the audio when the client joins
     @transport.event_handler("on_client_connected")

examples/foundational/03-still-frame.py

@@ -51,7 +51,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             key=os.getenv("FAL_KEY"),
         )
 
-        task = PipelineTask(Pipeline([imagegen, transport.output()]))
+        task = PipelineTask(
+            Pipeline([imagegen, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
         # Register an event handler so we can play the audio when the client joins
         @transport.event_handler("on_client_connected")

examples/foundational/03b-still-frame-imagen.py

@@ -52,6 +52,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     # Register an event handler so we can play the audio when the client joins

examples/foundational/04-transports-small-webrtc.py

@@ -110,7 +110,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         logger.info(f"Client disconnected")
         await task.cancel()
 
-    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+    runner = PipelineRunner(handle_sigint=False)
 
     await runner.run(task)
 

examples/foundational/05-sync-speech-and-image.py

@@ -155,7 +155,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             frames.append(MonthFrame(month=month))
             frames.append(LLMMessagesFrame(messages))
 
-        task = PipelineTask(pipeline)
+        task = PipelineTask(
+            pipeline,
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
         # Set up transport event handlers
         @transport.event_handler("on_client_connected")

examples/foundational/06-listen-and-respond.py

@@ -119,6 +119,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/06a-image-sync.py

@@ -137,6 +137,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07-interruptible-cartesia-http.py

@@ -88,6 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07-interruptible.py

@@ -87,6 +87,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07a-interruptible-speechmatics-vad.py

@@ -146,6 +146,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07a-interruptible-speechmatics.py

@@ -129,6 +129,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07aa-interruptible-soniox.py

@@ -86,6 +86,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07ab-interruptible-inworld-http.py

@@ -101,6 +101,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07ac-interruptible-asyncai-http.py

@@ -93,6 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07ac-interruptible-asyncai.py

@@ -89,6 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07b-interruptible-langchain.py

@@ -118,6 +118,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -92,6 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @stt.event_handler("on_speech_started")

examples/foundational/07c-interruptible-deepgram.py

@@ -86,6 +86,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -93,6 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07d-interruptible-elevenlabs.py

@@ -89,6 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07e-interruptible-playht-http.py

@@ -89,6 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07e-interruptible-playht.py

@@ -91,6 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07f-interruptible-azure.py

@@ -95,6 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07g-interruptible-openai.py

@@ -90,6 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07h-interruptible-openpipe.py

@@ -94,6 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07i-interruptible-xtts.py

@@ -92,6 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07j-interruptible-gladia.py

@@ -55,6 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY", ""),
+        region=os.getenv("GLADIA_REGION"),
         params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],
@@ -97,6 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07k-interruptible-lmnt.py

@@ -85,6 +85,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07l-interruptible-groq.py

@@ -90,6 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07m-interruptible-aws.py

@@ -91,6 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07n-interruptible-google.py

@@ -98,6 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07o-interruptible-assemblyai.py

@@ -91,6 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07p-interruptible-krisp.py

@@ -89,6 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07q-interruptible-rime-http.py

@@ -94,6 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07q-interruptible-rime.py

@@ -88,6 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07r-interruptible-riva-nim.py

@@ -85,6 +85,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07s-interruptible-google-audio-in.py

@@ -266,6 +266,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07t-interruptible-fish.py

@@ -89,6 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07u-interruptible-ultravox.py

@@ -82,6 +82,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -93,6 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07v-interruptible-neuphonic.py

@@ -88,6 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07w-interruptible-fal.py

@@ -91,6 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/07y-interruptible-minimax.py

@@ -95,6 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/07z-interruptible-sarvam.py

@@ -94,6 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")

examples/foundational/09-mirror.py

@@ -80,6 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     task = PipelineTask(
         pipeline,
         params=PipelineParams(),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/09a-local-mirror.py

@@ -97,6 +97,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     task = PipelineTask(
         pipeline,
         params=PipelineParams(),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     async def run_tk():

examples/foundational/10-wake-phrase.py

@@ -92,6 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/11-sound-effects.py

@@ -143,7 +143,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
     )
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):

examples/foundational/12-describe-video.py

@@ -103,7 +103,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
     )
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):

examples/foundational/12a-describe-video-gemini-flash.py

@@ -109,6 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/12b-describe-video-gpt-4o.py

@@ -109,6 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/12c-describe-video-anthropic.py

@@ -109,6 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/13-whisper-transcription.py

@@ -60,7 +60,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13b-deepgram-transcription.py

@@ -54,7 +54,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13c-gladia-transcription.py

@@ -47,6 +47,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
+        region=os.getenv("GLADIA_REGION"),
         # live_options=LiveOptions(language=Language.FR),
     )
 
@@ -54,7 +55,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13c-gladia-translation.py

@@ -56,6 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
+        region=os.getenv("GLADIA_REGION"),
         params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],  # Input in English
@@ -75,7 +76,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13d-assemblyai-transcription.py

@@ -53,7 +53,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13e-whisper-mlx.py

@@ -87,6 +87,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/13f-cartesia-transcription.py

@@ -54,7 +54,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13g-sambanova-transcription.py

@@ -91,6 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/13h-speechmatics-transcription.py

@@ -74,7 +74,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/13i-soniox-transcription.py

@@ -60,7 +60,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     pipeline = Pipeline([transport.input(), stt, tl])
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/14-function-calling.py

@@ -138,6 +138,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14a-function-calling-anthropic.py

@@ -132,6 +132,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14b-function-calling-anthropic-video.py

@@ -180,6 +180,7 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14c-function-calling-together.py

@@ -124,6 +124,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14d-function-calling-video.py

@@ -169,6 +169,7 @@ indicate you should use the get_image tool are:
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14e-function-calling-google.py

@@ -191,6 +191,7 @@ indicate you should use the get_image tool are:
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14f-function-calling-groq.py

@@ -126,6 +126,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14g-function-calling-grok.py

@@ -116,6 +116,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14h-function-calling-azure.py

@@ -125,6 +125,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14i-function-calling-fireworks.py

@@ -124,6 +124,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14j-function-calling-nim.py

@@ -122,6 +122,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14k-function-calling-cerebras.py

@@ -131,6 +131,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14l-function-calling-deepseek.py

@@ -131,6 +131,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14m-function-calling-openrouter.py

@@ -63,8 +63,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
     tts = AzureTTSService(
-        api_key=os.getenv("AZURE_API_KEY"),
-        region="eastus",
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
         voice="en-US-JennyNeural",
         params=AzureTTSService.InputParams(language="en-US", rate="1.1", style="cheerful"),
     )
@@ -125,6 +125,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14n-function-calling-perplexity.py

@@ -94,6 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14o-function-calling-gemini-openai-format.py

@@ -121,6 +121,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14p-function-calling-gemini-vertex-ai.py

@@ -127,6 +127,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14q-function-calling-qwen.py

@@ -123,6 +123,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14r-function-calling-aws.py

@@ -137,6 +137,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14s-function-calling-sambanova.py

@@ -130,6 +130,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14t-function-calling-direct.py

@@ -124,6 +124,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14u-function-calling-ollama.py

@@ -140,6 +140,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/14v-function-calling-openai.py

@@ -0,0 +1,176 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.openai.stt import OpenAISTTService
+from pipecat.services.openai.tts import OpenAITTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = OpenAISTTService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        model="gpt-4o-transcribe",
+        prompt="Expect words related weather, such as temperature and conditions. And restaurant names.",
+    )
+
+    # voice choices: ash, ballad, or any other voice available in the OpenAI TTS API
+    # see https://www.openai.fm/
+    tts = OpenAITTSService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        voice="ballad",
+        instructions="Please speak clearly and at a moderate pace.",
+    )
+
+    # model choices: gpt-4o, gpt-4.1, etc.
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/15-switch-voices.py

@@ -155,6 +155,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/15a-switch-languages.py

@@ -143,6 +143,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/16-gpu-container-local-bot.py

@@ -95,6 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     # When the first participant joins, the bot should introduce itself.

examples/foundational/17-detect-user-idle.py

@@ -122,6 +122,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")

examples/foundational/18-gstreamer-filesrc.py

@@ -63,7 +63,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
     )
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 

examples/foundational/18a-gstreamer-videotestsrc.py

@@ -55,7 +55,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
     )
 
-    task = PipelineTask(pipeline)
+    task = PipelineTask(
+        pipeline,
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 

examples/foundational/19-openai-realtime-beta.py

@@ -191,6 +191,7 @@ Remember, your responses should be short. Just one or two sentences, usually."""
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
     @transport.event_handler("on_client_connected")