Add error handling for unsupported files

This PR introduces:
1. a new /files/ POST endpoint in the local runner that supports
   uploading a file to a folder that must be provided at runtime
2. By default, the runner will allow a maximum 10 files to be
   saved
3. Added logic to the send-file handler in RTVI to read a file
   from disk if the file provide is a url starting with '/files/'

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/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

@@ -58,7 +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/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

@@ -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/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/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)

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

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("TOGETHER_API_KEY"),
         settings=TogetherLLMService.Settings(
             model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
-            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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -99,7 +99,7 @@ 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 able to describe images from the user camera.",
+            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 able to describe images from the user camera.",
         ),
     )
     llm.register_function("fetch_user_image", fetch_user_image)

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

@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
             # which we need for image input.
             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 able to describe images from the user camera.",
+            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 able to describe images from the user camera.",
         ),
     )
     llm.register_function("fetch_user_image", fetch_user_image)

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

@@ -99,7 +99,7 @@ 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 able to describe images from the user camera.",
+            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 able to describe images from the user camera.",
         ),
     )
     llm.register_function("fetch_user_image", fetch_user_image)

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

@@ -129,7 +129,7 @@ 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 able to describe images from the user camera.",
+            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 able to describe images from the user camera.",
         ),
     )
     llm.register_function("fetch_user_image", fetch_user_image)

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

@@ -99,7 +99,7 @@ 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 able to describe images from the user camera.",
+            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 able to describe images from the user camera.",
         ),
     )
     llm.register_function("fetch_user_image", fetch_user_image)

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GroqLLMService(
         api_key=os.getenv("GROQ_API_KEY"),
         settings=GroqLLMService.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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GrokLLMService(
         api_key=os.getenv("GROK_API_KEY"),
         settings=GrokLLMService.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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -74,7 +74,7 @@ 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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("FIREWORKS_API_KEY"),
         settings=FireworksLLMService.Settings(
             model="accounts/fireworks/models/gpt-oss-20b",
-            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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
             # Recommended when turning thinking off
             temperature=0.0,
-            system_instruction="/no_think 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="/no_think 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 can also register a function_name of None to get all functions

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = CerebrasLLMService(
         api_key=os.getenv("CEREBRAS_API_KEY"),
         settings=CerebrasLLMService.Settings(
-            system_instruction="""You are a helpful LLM 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. 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 have one functions available:
 

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

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("DEEPSEEK_API_KEY"),
         settings=DeepSeekLLMService.Settings(
             model="deepseek-chat",
-            system_instruction="""You are a helpful LLM 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. 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 have one functions available:
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("OPENROUTER_API_KEY"),
         settings=OpenRouterLLMService.Settings(
             model="openai/gpt-4o-2024-11-20",
-            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.",
         ),
     )
     # You can also register a function_name of None to get all functions

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

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = PerplexityLLMService(
         api_key=os.getenv("PERPLEXITY_API_KEY"),
         settings=PerplexityLLMService.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, but try to be 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/14o-function-calling-gemini-openai-format.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMOpenAIBetaService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         settings=GoogleLLMOpenAIBetaService.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.",
         ),
     )
     # You can aslo register a function_name of None to get all functions

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         project_id=os.getenv("GOOGLE_CLOUD_PROJECT_ID"),
         location=os.getenv("GOOGLE_CLOUD_LOCATION"),
         settings=GoogleVertexLLMService.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.",
         ),
     )
     # You can aslo register a function_name of None to get all functions

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

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("QWEN_API_KEY"),
         model="qwen2.5-72b-instruct",
         settings=QwenLLMService.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/14r-function-calling-aws.py

@@ -78,7 +78,7 @@ 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/14s-function-calling-sambanova.py

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = SambaNovaLLMService(
         api_key=os.getenv("SAMBANOVA_API_KEY"),
         settings=SambaNovaLLMService.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.",
         ),
     )
     # You can also register a function_name of None to get all functions