pass config through to static route

Changing heygen log level to trace.

CHANGELOG.md

@@ -5,6 +5,29 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- Added `MistralLLMService`, using Mistral's chat completion API.
+
+- For `OpenAILLMService` and its subclasses, added the ability to retry
+  executing a chat completion after a timeout period. The new args are
+  `retry_timeout_secs` and `retry_on_timeout`. This feature is disabled by
+  default.
+
+### Fixed
+
+- Fixed an `AudioBufferProcessor` issues that would cause audio overlap when
+  setting a max buffer size.
+
+- Fixed an issue where `AsyncAITTSService` had very high latency in responding
+  by adding `force=true` when sending the flush command.
+
+### Other
+
+- Added `14w-function-calling-mistal.py` using `MistralLLMService`.
+
 ## [0.0.80] - 2025-08-13
 
 ### Added
@@ -13,11 +36,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   Gemini model can be prompted to insert styled speech to control the TTS
   output.
 
-- For `OpenAILLMService` and its subclasses, added the ability to retry
-  executing a chat completion after a timeout period. The new args are
-  `retry_timeout_secs` and `retry_on_timeout`. This feature is disabled by
-  default.
-
 - Added Exotel support to Pipecat's development runner. You can now connect
   using the runner with `uv run bot.py -t exotel` and an ngrok connection to
   HTTP port 7860.

README.md

@@ -54,7 +54,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                          |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                          |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
 | Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
 | Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |

examples/foundational/14w-function-calling-mistral.py

@@ -0,0 +1,165 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.mistral.llm import MistralLLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = MistralLLMService(api_key=os.getenv("MISTRAL_API_KEY"))
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/README.md

@@ -4,40 +4,32 @@ This directory contains examples showing how to build voice and multimodal agent
 
 ## Setup
 
-1. Make sure you have uv installed:
+1. Follow the [README](../../README.md#%EF%B8%8F-contributing-to-the-framework) steps to get your local environment configured.
 
-   ```bash
-   curl -LsSf https://astral.sh/uv/install.sh | sh
-   ```
+   > **Run from root directory**: Make sure you are running the steps from the root directory.
 
-   > **Need help?** Refer to the [uv install documentation](https://docs.astral.sh/uv/getting-started/installation/).
+   > **Using local audio?**: The `LocalAudioTransport` requires a system dependency for `portaudio`. Install the dependency to use the transport.
 
-2. Create a venv and install example dependencies:
-
-   ```bash
-   uv sync --all-extras --no-extra krisp
-   ```
-
-3. Create a `.env` file with your API keys:
+2. Copy the [`env.example`](../../env.example) file and add API keys for services you plan to use:
 
    ```bash
    cp env.example .env
    # Edit .env with your API keys
    ```
 
-4. Navigate to the examples directory:
+3. Navigate to the examples directory if you aren't already there:
 
    ```bash
    cd examples/foundational
    ```
 
-5. Run any example:
+4. Run any example:
 
    ```bash
    uv run python 01-say-one-thing.py
    ```
 
-6. Open the web interface at http://localhost:7860/client/ and click "Connect"
+5. Open the web interface at http://localhost:7860/client/ and click "Connect"
 
 ## Running examples with other transports
 

pyproject.toml

@@ -73,6 +73,7 @@ lmnt = [ "websockets>=13.1,<15.0" ]
 local = [ "pyaudio~=0.2.14" ]
 mcp = [ "mcp[cli]~=1.9.4" ]
 mem0 = [ "mem0ai~=0.1.94" ]
+mistral = []
 mlx-whisper = [ "mlx-whisper~=0.4.2" ]
 moondream = [ "accelerate~=1.10.0", "einops~=0.8.0", "pyvips[binary]~=3.0.0", "timm~=1.0.13", "transformers>=4.48.0" ]
 nim = []

scripts/evals/run-release-evals.py

@@ -113,6 +113,7 @@ TESTS_14 = [
     ("14q-function-calling-qwen.py", PROMPT_WEATHER, EVAL_WEATHER),
     ("14r-function-calling-aws.py", PROMPT_WEATHER, EVAL_WEATHER),
     ("14v-function-calling-openai.py", PROMPT_WEATHER, EVAL_WEATHER),
+    ("14w-function-calling-mistral.py", PROMPT_WEATHER, EVAL_WEATHER),
     # Currently not working.
     # ("14c-function-calling-together.py", PROMPT_WEATHER, EVAL_WEATHER),
     # ("14k-function-calling-cerebras.py", PROMPT_WEATHER, EVAL_WEATHER),

src/pipecat/processors/audio/audio_buffer_processor.py

@@ -178,6 +178,7 @@ class AudioBufferProcessor(FrameProcessor):
         Calls audio handlers with any remaining buffered audio before stopping.
         """
         await self._call_on_audio_data_handler()
+        self._reset_recording()
         self._recording = False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
@@ -230,6 +231,7 @@ class AudioBufferProcessor(FrameProcessor):
 
         if self._buffer_size > 0 and len(self._user_audio_buffer) > self._buffer_size:
             await self._call_on_audio_data_handler()
+            self._reset_recording()
 
         # Process turn recording with preprocessed data.
         if self._enable_turn_audio:
@@ -288,8 +290,6 @@ class AudioBufferProcessor(FrameProcessor):
             self._num_channels,
         )
 
-        self._reset_audio_buffers()
-
     def _buffer_has_audio(self, buffer: bytearray) -> bool:
         """Check if a buffer contains audio data."""
         return buffer is not None and len(buffer) > 0

src/pipecat/runner/run.py

@@ -76,6 +76,7 @@ from loguru import logger
 
 from pipecat.runner.types import (
     DailyRunnerArguments,
+    SmallWebRTCPrebuiltArguments,
     SmallWebRTCRunnerArguments,
     WebSocketRunnerArguments,
 )
@@ -151,7 +152,11 @@ async def _run_telephony_bot(websocket: WebSocket):
 
 
 def _create_server_app(
-    transport_type: str, host: str = "localhost", proxy: str = None, esp32_mode: bool = False
+    transport_type: str,
+    host: str = "localhost",
+    proxy: str = None,
+    esp32_mode: bool = False,
+    prebuilt_ui_config: SmallWebRTCPrebuiltArguments = None,
 ):
     """Create FastAPI app with transport-specific routes."""
     app = FastAPI()
@@ -166,9 +171,9 @@ def _create_server_app(
 
     # Set up transport-specific routes
     if transport_type == "webrtc":
-        _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host)
+        _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host, prebuilt_ui_config=prebuilt_ui_config)
     elif transport_type == "daily":
-        _setup_daily_routes(app)
+        _setup_daily_routes(app, prebuilt_ui_config=prebuilt_ui_config)
     elif transport_type in ["twilio", "telnyx", "plivo", "exotel"]:
         _setup_telephony_routes(app, transport_type, proxy)
     else:
@@ -177,7 +182,12 @@ def _create_server_app(
     return app
 
 
-def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "localhost"):
+def _setup_webrtc_routes(
+    app: FastAPI,
+    esp32_mode: bool = False,
+    host: str = "localhost",
+    prebuilt_ui_config: SmallWebRTCPrebuiltArguments = None,
+):
     """Set up WebRTC-specific routes."""
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
@@ -191,7 +201,7 @@ def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "lo
     pcs_map: Dict[str, SmallWebRTCConnection] = {}
 
     # Mount the frontend
-    app.mount("/client", SmallWebRTCPrebuiltUI)
+    app.mount("/client", SmallWebRTCPrebuiltUI(config=prebuilt_ui_config))
 
     @app.get("/", include_in_schema=False)
     async def root_redirect():
@@ -402,6 +412,7 @@ async def _run_daily_direct():
 
         # Direct connections have no request body, so use empty dict
         runner_args = DailyRunnerArguments(room_url=room_url, token=token)
+        runner_args.handle_sigint = True
 
         # Get the bot module and run it directly
         bot_module = _get_bot_module()
@@ -434,7 +445,7 @@ def _validate_and_clean_proxy(proxy: str) -> str:
     return proxy
 
 
-def main():
+def main(prebuilt_ui_config: SmallWebRTCPrebuiltArguments = None):
     """Start the Pipecat development runner.
 
     Parses command-line arguments and starts a FastAPI server configured
@@ -532,7 +543,7 @@ def main():
         print()
 
     # Create the app with transport-specific setup
-    app = _create_server_app(args.transport, args.host, args.proxy, args.esp32)
+    app = _create_server_app(args.transport, args.host, args.proxy, args.esp32, prebuilt_ui_config)
 
     # Run the server
     uvicorn.run(app, host=args.host, port=args.port)

src/pipecat/runner/types.py

@@ -65,3 +65,67 @@ class SmallWebRTCRunnerArguments(RunnerArguments):
     """
 
     webrtc_connection: Any
+
+
+@dataclass
+class SmallWebRTCPrebuiltArguments:
+    """Arguments for Small WebRTC prebuilt console template.
+
+    Parameters:
+        no_rtvi: Disables RTVI related functionality. Default: False
+        server_rtvi_version: Specifies the RTVI version in use by the server. Default: None
+        no_user_audio: Disables user audio input entirely. Default: False
+        no_user_video: Disables user video input entirely. Default: False
+        user_video_enabled: Enables user video input. Default: False
+        user_audio_enabled: Enables user audio input. Default: True
+        no_audio_output: Disables audio output for the bot. Default: False
+        no_bot_audio: Disables audio visualization for the bot. Default: False
+        no_bot_video: Disables video visualization for the bot. Default: True
+        transport_type: Type of transport to use for the RTVI client. Default: "smallwebrtc"
+        transport_options: Options for configuring the transport. Default: None
+        connect_params: Parameters for connecting to the transport. Default: None
+        client_options: Options for configuring the RTVI client. Default: None
+        theme: Theme to use for the UI. Default: "system"
+        no_theme_switch: Disables the theme switcher in the header. Default: False
+        no_logo: Disables the logo in the header. Default: False
+        no_session_info: Disables the session info panel. Default: False
+        no_status_info: Disables the status info panel. Default: False
+        title_text: Title displayed in the header. Default: "Pipecat Playground"
+        assistant_label_text: Label for assistant messages. Default: "assistant"
+        user_label_text: Label for user messages. Default: "user"
+        system_label_text: Label for system messages. Default: "system"
+        collapse_info_panel: Whether to collapse the info panel by default. Default: False
+        collapse_media_panel: Whether to collapse the media panel by default. Default: False
+    """
+
+    # RTVI configuration
+    no_rtvi: bool = False
+    server_rtvi_version: Optional[str] = None
+
+    # Media configuration
+    no_user_audio: bool = False
+    no_user_video: bool = False
+    user_video_enabled: bool = False
+    user_audio_enabled: bool = True
+    no_audio_output: bool = False
+    no_bot_audio: bool = False
+    no_bot_video: bool = True
+
+    # Client & transport configuration
+    transport_type: str = "smallwebrtc"
+    transport_options: Optional[Any] = None
+    connect_params: Optional[Any] = None
+    client_options: Optional[Any] = None
+
+    # UI configuration
+    theme: str = "system"
+    no_theme_switch: bool = False
+    no_logo: bool = False
+    no_session_info: bool = False
+    no_status_info: bool = False
+    title_text: str = "Pipecat Playground"
+    assistant_label_text: str = "assistant"
+    user_label_text: str = "user"
+    system_label_text: str = "system"
+    collapse_info_panel: bool = False
+    collapse_media_panel: bool = False

src/pipecat/services/asyncai/tts.py

@@ -335,7 +335,7 @@ class AsyncAITTSService(InterruptibleTTSService):
                 yield TTSStartedFrame()
                 self._started = True
 
-            msg = self._build_msg(text=text)
+            msg = self._build_msg(text=text, force=True)
 
             try:
                 await self._get_websocket().send(msg)

src/pipecat/services/elevenlabs/tts.py

@@ -495,6 +495,7 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
                 if self._context_id:
                     await self._websocket.send(json.dumps({"close_socket": True}))
                 await self._websocket.close()
+                logger.debug("Disconnected from ElevenLabs")
         except Exception as e:
             logger.error(f"{self} error closing websocket: {e}")
         finally:

src/pipecat/services/heygen/client.py

@@ -248,7 +248,7 @@ class HeyGenClient:
         if event_type == "agent.state":
             logger.debug(f"HeyGenClient ws received agent status: {event}")
         else:
-            logger.error(f"HeyGenClient ws received unknown event: {event_type}")
+            logger.trace(f"HeyGenClient ws received unknown event: {event_type}")
 
     async def _ws_disconnect(self) -> None:
         """Disconnect from HeyGen websocket endpoint."""

src/pipecat/services/mistral/llm.py

@@ -0,0 +1,182 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Mistral LLM service implementation using OpenAI-compatible interface."""
+
+from typing import List, Sequence
+
+from loguru import logger
+from openai import AsyncStream
+from openai.types.chat import ChatCompletionChunk, ChatCompletionMessageParam
+
+from pipecat.frames.frames import FunctionCallFromLLM
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.openai.llm import OpenAILLMService
+
+
+class MistralLLMService(OpenAILLMService):
+    """A service for interacting with Mistral's API using the OpenAI-compatible interface.
+
+    This service extends OpenAILLMService to connect to Mistral's API endpoint while
+    maintaining full compatibility with OpenAI's interface and functionality.
+    """
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        base_url: str = "https://api.mistral.ai/v1",
+        model: str = "mistral-small-latest",
+        **kwargs,
+    ):
+        """Initialize the Mistral LLM service.
+
+        Args:
+            api_key: The API key for accessing Mistral's API.
+            base_url: The base URL for Mistral API. Defaults to "https://api.mistral.ai/v1".
+            model: The model identifier to use. Defaults to "mistral-small-latest".
+            **kwargs: Additional keyword arguments passed to OpenAILLMService.
+        """
+        super().__init__(api_key=api_key, base_url=base_url, model=model, **kwargs)
+
+    def create_client(self, api_key=None, base_url=None, **kwargs):
+        """Create OpenAI-compatible client for Mistral API endpoint.
+
+        Args:
+            api_key: The API key for authentication. If None, uses instance key.
+            base_url: The base URL for the API. If None, uses instance URL.
+            **kwargs: Additional arguments passed to the client constructor.
+
+        Returns:
+            An OpenAI-compatible client configured for Mistral API.
+        """
+        logger.debug(f"Creating Mistral client with api {base_url}")
+        return super().create_client(api_key, base_url, **kwargs)
+
+    def _apply_mistral_assistant_prefix(
+        self, messages: List[ChatCompletionMessageParam]
+    ) -> List[ChatCompletionMessageParam]:
+        """Apply Mistral's assistant message prefix requirement.
+
+        Mistral requires assistant messages to have prefix=True when they
+        are the final message in a conversation. According to Mistral's API:
+        - Assistant messages with prefix=True MUST be the last message
+        - Only add prefix=True to the final assistant message when needed
+        - This allows assistant messages to be accepted as the last message
+
+        Args:
+            messages: The original list of messages.
+
+        Returns:
+            Messages with Mistral prefix requirement applied to final assistant message.
+        """
+        if not messages:
+            return messages
+
+        # Create a copy to avoid modifying the original
+        fixed_messages = [dict(msg) for msg in messages]
+
+        # Get the last message
+        last_message = fixed_messages[-1]
+
+        # Only add prefix=True to the last message if it's an assistant message
+        # and Mistral would otherwise reject it
+        if last_message.get("role") == "assistant" and "prefix" not in last_message:
+            last_message["prefix"] = True
+
+        return fixed_messages
+
+    async def run_function_calls(self, function_calls: Sequence[FunctionCallFromLLM]):
+        """Execute function calls, filtering out already-completed ones.
+
+        Mistral and OpenAI have different function call detection patterns:
+
+        OpenAI (Stream-based detection):
+        - Detects function calls only from streaming chunks as the LLM generates them
+        - Second LLM completion doesn't re-detect existing tool_calls in message history
+        - Function calls execute exactly once
+
+        Mistral (Message-based detection):
+        - Detects function calls from the complete message history on each completion
+        - Second LLM completion with the response re-detects the same tool_calls from
+          previous messages
+        - Without filtering, function calls would execute twice
+
+        This method prevents duplicate execution by:
+        1. Checking message history for existing tool result messages
+        2. Filtering out function calls that already have corresponding results
+        3. Only executing function calls that haven't been completed yet
+
+        Note: This filtering prevents duplicate function execution, but the
+        on_function_calls_started event may still fire twice due to the detection
+        pattern difference. This is expected behavior.
+
+        Args:
+            function_calls: The function calls to potentially execute.
+        """
+        if not function_calls:
+            return
+
+        # Filter out function calls that already have results
+        calls_to_execute = []
+
+        # Get messages from the first function call's context (they should all have the same context)
+        messages = function_calls[0].context.get_messages() if function_calls else []
+
+        # Get all tool_call_ids that already have results
+        executed_call_ids = set()
+        for msg in messages:
+            if msg.get("role") == "tool" and msg.get("tool_call_id"):
+                executed_call_ids.add(msg.get("tool_call_id"))
+
+        # Only include function calls that haven't been executed yet
+        for call in function_calls:
+            if call.tool_call_id not in executed_call_ids:
+                calls_to_execute.append(call)
+            else:
+                logger.trace(
+                    f"Skipping already-executed function call: {call.function_name}:{call.tool_call_id}"
+                )
+
+        # Call parent method with filtered list
+        if calls_to_execute:
+            await super().run_function_calls(calls_to_execute)
+
+    def build_chat_completion_params(
+        self, context: OpenAILLMContext, messages: List[ChatCompletionMessageParam]
+    ) -> dict:
+        """Build parameters for Mistral chat completion request.
+
+        Handles Mistral-specific requirements including:
+        - Assistant message prefix requirement for API compatibility
+        - Parameter mapping (random_seed instead of seed)
+        - Core completion settings
+        """
+        # Apply Mistral's assistant prefix requirement for API compatibility
+        fixed_messages = self._apply_mistral_assistant_prefix(messages)
+
+        params = {
+            "model": self.model_name,
+            "stream": True,
+            "messages": fixed_messages,
+            "tools": context.tools,
+            "tool_choice": context.tool_choice,
+            "frequency_penalty": self._settings["frequency_penalty"],
+            "presence_penalty": self._settings["presence_penalty"],
+            "temperature": self._settings["temperature"],
+            "top_p": self._settings["top_p"],
+            "max_tokens": self._settings["max_tokens"],
+        }
+
+        # Handle Mistral-specific parameter mapping
+        # Mistral uses "random_seed" instead of "seed"
+        if self._settings["seed"]:
+            params["random_seed"] = self._settings["seed"]
+
+        # Add any extra parameters
+        params.update(self._settings["extra"])
+
+        return params