fix: propagate append_to_context from TextFrame through TTS _process_text_frame

Co-authored-by: jamsea <614910+jamsea@users.noreply.github.com>

COMMUNITY_INTEGRATIONS.md

@@ -280,17 +280,17 @@ from typing import Optional
 
 class MyTTSService(TTSService):
     Settings = MyTTSSettings
-    _settings: MyTTSSettings
+    _settings: Settings
 
     def __init__(
         self,
         *,
         api_key: str,
-        settings: Optional[MyTTSSettings] = None,
+        settings: Optional[Settings] = None,
         **kwargs,
     ):
         # 1. Defaults — every field has a real value (store mode).
-        default_settings = MyTTSSettings(
+        default_settings = self.Settings(
             model="my-model-v1",
             voice="default-voice",
             language="en",

changelog/3457.changed.md

@@ -0,0 +1 @@
+- Changed tool result JSON serialization to use `ensure_ascii=False`, preserving UTF-8 characters instead of escaping them. This reduces context size and token usage for non-English languages.

changelog/3991.changed.md

@@ -0,0 +1 @@
+- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of `OpenAIRealtimeSTTSettings`, making it runtime-updatable via `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is deprecated as of 0.0.106.

changelog/3997.changed.md

@@ -0,0 +1 @@
+- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable release).

changelog/4000.fixed.md

@@ -0,0 +1 @@
+- Fixed an issue where the default model for `OpenAILLMService` and `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now restored to `gpt-4.1`.

changelog/4001.changed.md

@@ -0,0 +1 @@
+- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`, aligning it with the HeyGen and Tavus video services. It supports `SimliVideoService.Settings(...)` for configuration and uses `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage (`api_key`, `face_id`, etc.) remains unchanged.

changelog/4001.deprecated.md

@@ -0,0 +1 @@
+- `SimliVideoService.InputParams` is deprecated. Use the direct constructor parameters `max_session_length`, `max_idle_time`, and `enable_logging` instead.

changelog/4004.added.md

@@ -0,0 +1 @@
+- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `STTUpdateSettingsFrame`) to target a specific service instance. When `service` is set, only the matching service applies the settings; others forward the frame unchanged. This enables updating a single service when multiple services of the same type exist in the pipeline.

changelog/4005.added.md

@@ -0,0 +1 @@
+- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily runner. These convenience parameters let callers specify a SIP provider name and geographic region directly without manually constructing `DailyRoomProperties` and `DailyRoomSipParams`.

changelog/4006.fixed.md

@@ -0,0 +1 @@
+- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut down before in-flight frames (e.g. LLM function call responses) finished processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline as `ControlFrame`s, ensuring all pending work is flushed before shutdown begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate (`SystemFrame`).

changelog/4007.fixed.2.md

@@ -0,0 +1 @@
+- Fixed `TTSService` potentially canceling in-flight audio during shutdown. The stop sequence now waits for all queued audio contexts to finish processing before canceling the stop frame task.

changelog/4007.fixed.md

@@ -0,0 +1 @@
+- Fixed `ParallelPipeline` dropping or misordering frames during lifecycle synchronization. Buffered frames are now flushed in the correct order relative to synchronization frames (`StartFrame` goes first, `EndFrame`/`CancelFrame` go after), and frames added to the buffer during flush are also drained.

changelog/4009.added.md

@@ -0,0 +1 @@
+- Added `PerplexityLLMAdapter` that automatically transforms conversation messages to satisfy Perplexity's stricter API constraints (strict role alternation, no non-initial system messages, last message must be user/tool). Previously, certain conversation histories could cause Perplexity API errors that didn't occur with OpenAI (`PerplexityLLMService` subclasses `OpenAILLMService` since Perplexity uses an OpenAI-compatible API).

changelog/4012.deprecated.md

@@ -0,0 +1 @@
+- Deprecated `LocalSmartTurnAnalyzerV2` and `LocalCoreMLSmartTurnAnalyzer`. Use `LocalSmartTurnAnalyzerV3` instead. Instantiating these analyzers will now emit a `DeprecationWarning`.

changelog/4023.changed.md

@@ -0,0 +1 @@
+- Update `pipecat-ai-small-webrtc-prebuilt` to `2.4.0`.

changelog/4024.fixed.md

@@ -0,0 +1 @@
+- Fixed `Language` enum values (e.g. `Language.ES`) not being converted to service-specific codes when passed via `settings=Service.Settings(language=Language.ES)` at init time. This caused API errors (e.g. 400 from Rime) because the raw enum was sent instead of the expected language code (e.g. `"spa"`). Runtime updates via `UpdateSettingsFrame` were unaffected. The fix centralizes conversion in the base `TTSService` and `STTService` classes so all services handle this consistently.

changelog/4026.fixed.md

@@ -0,0 +1 @@
+- Fixed `DeepgramSTTService` ignoring the `base_url` scheme when using `ws://` or `http://`. Previously these were silently overwritten with `wss://` / `https://`, breaking air-gapped or private deployments that don't use TLS. All scheme choices (`wss://`, `https://`, `ws://`, `http://`, or bare hostname) are now respected.

changelog/4035.security.md

@@ -0,0 +1 @@
+- Bumped PyJWT minimum version from 2.10.1 to 2.12.0 in the `livekit` extra to address CVE-2026-32597 (GHSA-752w-5fwx-jx9f), where PyJWT <= 2.11.0 accepted unknown `crit` header extensions.

changelog/4037.fixed.md

@@ -0,0 +1 @@
+- Fixed `LLMSwitcher.register_function()` and `register_direct_function()` not accepting or forwarding the `timeout_secs` parameter.

changelog/4046.fixed.md

@@ -0,0 +1 @@
+Fixed `SonioxSTTService` and `OpenAIRealtimeSTTService` crash when language parameters contain plain strings instead of `Language` enum values.

changelog/4047.added.md

@@ -0,0 +1 @@
+- Added DTMF input event support to the Daily transport. Incoming DTMF tones are now received via Daily's `on_dtmf_event` callback and pushed into the pipeline as `InputDTMFFrame`, enabling bots to react to keypad presses from phone callers.

changelog/4047.changed.md

@@ -0,0 +1 @@
+- Updated `daily-python` dependency to 0.25.0.

changelog/4048.changed.md

@@ -0,0 +1 @@
+- Added `enable_dialout` parameter to `configure()` in `pipecat.runner.daily` to support dial-out rooms. Also narrowed misleading `Optional` type hints and deduplicated token expiry calculation.

changelog/4057.fixed.md

@@ -0,0 +1 @@
+- Fixed premature user turn stops caused by late transcriptions arriving between turns. A stale transcript from the previous turn could persist into the next turn and trigger a stop before the current turn's real transcript arrived. Stop strategies are now reset at both turn start and turn stop to prevent state from leaking across turn boundaries.

changelog/4058.fixed.md

@@ -0,0 +1 @@
+- Fixed raw language strings like `"de-DE"` silently failing when passed to TTS/STT services (e.g. ElevenLabs producing no audio). Raw strings now go through the same `Language` enum resolution as enum values, so regional codes like `"de-DE"` are properly converted to service-expected formats like `"de"`. Unrecognized strings log a warning instead of failing silently.

changelog/4063.fixed.md

@@ -0,0 +1 @@
+- Fixed Deepgram STT list-type settings (`keyterm`, `keywords`, `search`, `redact`, `replace`) being stringified instead of passed as lists to the SDK, which caused them to be sent as literal strings (e.g. `"['pipecat']"`) in the WebSocket query params.

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

@@ -47,7 +47,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -75,7 +75,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/04a-transports-daily.py

@@ -58,8 +58,7 @@ async def main():
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                model="gpt-4o",
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

examples/foundational/04b-transports-livekit.py

@@ -58,7 +58,7 @@ async def main():
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -91,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -108,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

examples/foundational/07-interruptible.py

@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -113,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
                 temperature=0.75,
-                system_instruction="You are a helpful British assistant called Sarah. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
+                system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
             ),
         )
 

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

@@ -93,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
                 temperature=0.75,
-                system_instruction="You are a helpful British assistant called Sarah. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
+                system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
             ),
         )
 

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

@@ -80,8 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             (
                 "system",
-                "Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. "
-                "Your response will be synthesized to voice and those characters will create unnatural sounds.",
+                "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
             MessagesPlaceholder("chat_history"),
             ("human", "{input}"),

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -79,7 +79,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         settings=AWSBedrockLLMSettings(
             model="us.amazon.nova-pro-v1:0",
             temperature=0.8,
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
         settings=AzureLLMService.Settings(
             model=os.getenv("AZURE_CHATGPT_MODEL"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
         settings=AzureLLMService.Settings(
             model=os.getenv("AZURE_CHATGPT_MODEL"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
         tags={"conversation_id": f"pipecat-{timestamp}"},
         settings=OpenPipeLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY", ""),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY", ""),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("GROQ_API_KEY"),
         settings=GroqLLMService.Settings(
             model="llama-3.1-8b-instant",
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         settings=AWSBedrockLLMService.Settings(
             model="us.anthropic.claude-sonnet-4-6",
             temperature=0.8,
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07n-interruptible-gemini-image.py

@@ -89,7 +89,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         settings=GoogleLLMService.Settings(
             model="gemini-2.5-flash-image",
             # model="gemini-3-pro-image-preview", # A more powerful model, but slower,
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
         settings=GoogleLLMService.Settings(
-            system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
+            system_instruction="""You are a helpful assistant in a voice conversation.
 
             IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
             - [sigh] - Insert a sigh sound
@@ -91,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             - "[whispering] Let me tell you a secret."
             - "The answer is... [long pause] ...42!"
 
-            Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.""",
+            Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise. Respond to what the user said in a creative and helpful way.""",
         ),
     )
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             model="gemini-2.5-flash",
             # force a certain amount of thinking if you want it
             # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             model="gemini-2.5-flash",
             # force a certain amount of thinking if you want it
             # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -115,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -93,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07r-interruptible-nvidia.py

@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("NVIDIA_API_KEY"),
         settings=NvidiaLLMService.Settings(
             model="meta/llama-3.3-70b-instruct",
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -48,7 +48,7 @@ load_dotenv(override=True)
 
 marker = "|----|"
 system_message = f"""
-You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief in your responses.
+You are a helpful LLM in a voice call. Your goals are to be helpful and brief in your responses.
 
 You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
 asked to transcribe what the user said, output an exact, word-for-word transcription.

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

@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

examples/foundational/07x-interruptible-local.py

@@ -52,7 +52,7 @@ async def main():
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
         )
 

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

@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07zd-interruptible-aicoustics.py

@@ -85,7 +85,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07ze-interruptible-hume.py

@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07zf-interruptible-gradium.py

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07zg-interruptible-camb.py

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
+            system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise.",
         ),
     )
 

examples/foundational/07zi-interruptible-piper.py

@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07zj-interruptible-kokoro.py

@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/07zk-interruptible-resemble.py

@@ -30,24 +30,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 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(),
     ),
 }
 
@@ -67,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/08-custom-frame-processor.py

@@ -103,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/10-wake-phrase.py

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/11-sound-effects.py

@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

examples/foundational/12-describe-image-openai.py

@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You are also able to describe images.",
         ),
     )
 

examples/foundational/12a-describe-image-anthropic.py

@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AnthropicLLMService(
         api_key=os.getenv("ANTHROPIC_API_KEY"),
         settings=AnthropicLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You are also able to describe images.",
         ),
     )
 

examples/foundational/12b-describe-image-aws.py

@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         settings=AWSBedrockLLMService.Settings(
             model="us.anthropic.claude-sonnet-4-6",
             temperature=0.8,
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You are also able to describe images.",
         ),
     )
 

examples/foundational/12c-describe-image-gemini-flash.py

@@ -61,7 +61,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         settings=GoogleLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You are also able to describe images.",
         ),
     )
 

examples/foundational/13-whisper-transcription.py

@@ -13,6 +13,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -40,15 +41,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -59,8 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = WhisperSTTService()
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13a-whisper-local.py

@@ -15,6 +15,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper.stt import WhisperSTTService
 from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
@@ -40,15 +41,15 @@ async def main():
     transport = LocalAudioTransport(
         LocalAudioTransportParams(
             audio_in_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
         )
     )
 
     stt = WhisperSTTService()
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(pipeline)
 

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

@@ -15,6 +15,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeaking
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -61,15 +62,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
 }
 
@@ -84,8 +82,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS))
+    )
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

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

@@ -16,6 +16,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeaking
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -62,15 +63,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
 }
 
@@ -86,8 +84,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS))
+    )
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

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

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,15 +40,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -60,8 +58,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13j-azure-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,15 +40,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -61,8 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13k-elevenlabs-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,11 +40,9 @@ class TranscriptionLogger(FrameProcessor):
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
-    "daily": lambda: DailyParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
-    "twilio": lambda: FastAPIWebsocketParams(
-        audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
-    ),
-    "webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+    "daily": lambda: DailyParams(audio_in_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
+    "webrtc": lambda: TransportParams(audio_in_enabled=True),
 }
 
 
@@ -53,8 +52,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13m-openai-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,11 +40,9 @@ class TranscriptionLogger(FrameProcessor):
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
-    "daily": lambda: DailyParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
-    "twilio": lambda: FastAPIWebsocketParams(
-        audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
-    ),
-    "webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+    "daily": lambda: DailyParams(audio_in_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
+    "webrtc": lambda: TransportParams(audio_in_enabled=True),
 }
 
 
@@ -59,8 +58,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/14-function-calling.py

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AnthropicLLMService(
         api_key=os.getenv("ANTHROPIC_API_KEY"),
         settings=AnthropicLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
         ),
     )
     llm.register_function("get_weather", get_weather)