diff --git a/README.md b/README.md index aec8577b9..2dd014d02 100644 --- a/README.md +++ b/README.md @@ -71,19 +71,19 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout ## 🧩 Available services -| 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), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [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), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [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), [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) | +| 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), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [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), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [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), [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), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [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), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [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), Ultravox, | -| 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 | -| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) | -| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) | -| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) | -| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) | -| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) | -| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) | +| 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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), Ultravox, | +| 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 | +| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) | +| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) | +| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) | +| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) | +| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) | +| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) | 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services) diff --git a/examples/foundational/51-grok-realtime.py b/examples/foundational/51-grok-realtime.py index 61eaeb062..efa1c9bac 100644 --- a/examples/foundational/51-grok-realtime.py +++ b/examples/foundational/51-grok-realtime.py @@ -25,7 +25,6 @@ Usage: python 50-grok-realtime.py --transport daily """ -import asyncio import os from datetime import datetime @@ -37,7 +36,7 @@ from pipecat.adapters.schemas.tools_schema import ToolsSchema # Note: Grok has built-in server-side VAD, so we don't need local VAD # from pipecat.audio.vad.silero import SileroVADAnalyzer -from pipecat.frames.frames import LLMRunFrame, LLMSetToolsFrame, TranscriptionMessage +from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage from pipecat.observers.loggers.transcription_log_observer import ( TranscriptionLogObserver, ) @@ -53,7 +52,6 @@ from pipecat.runner.types import RunnerArguments from pipecat.runner.utils import create_transport from pipecat.services.grok.realtime.events import ( SessionProperties, - TurnDetection, WebSearchTool, XSearchTool, ) @@ -173,11 +171,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): # Configure Grok session properties session_properties = SessionProperties( - # Voice options: Ara (warm, friendly), Rex (confident), Sal (smooth), - # Eve (energetic), Leo (authoritative) + # Voice options: Ara, Rex, Sal, Eve, Leo voice="Ara", - # Enable server-side VAD for automatic turn detection - turn_detection=TurnDetection(type="server_vad"), # System instructions instructions="""You are a helpful and friendly AI assistant powered by Grok. diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py index 19df05da9..297f33ae6 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -226,6 +226,11 @@ TESTS_50 = [ ("50-ultravox-realtime.py", EVAL_ORDER), ] + +TESTS_51 = [ + ("51-grok-realtime.py", EVAL_WEATHER), +] + TESTS = [ *TESTS_07, *TESTS_12, @@ -240,6 +245,7 @@ TESTS = [ *TESTS_44, *TESTS_49, *TESTS_50, + *TESTS_51, ] diff --git a/src/pipecat/services/grok/realtime/events.py b/src/pipecat/services/grok/realtime/events.py index d93aad233..7bc92b87f 100644 --- a/src/pipecat/services/grok/realtime/events.py +++ b/src/pipecat/services/grok/realtime/events.py @@ -205,7 +205,9 @@ class SessionProperties(BaseModel): Parameters: instructions: System instructions for the assistant. voice: The voice the model uses to respond. Options: Ara, Rex, Sal, Eve, Leo. - turn_detection: Configuration for turn detection, or None for manual. + Defaults to "Ara". + turn_detection: Configuration for turn detection. Defaults to server-side VAD. + Set to None for manual turn detection. audio: Configuration for input and output audio. tools: Available tools for the assistant (web_search, x_search, file_search, function). """ @@ -215,7 +217,9 @@ class SessionProperties(BaseModel): instructions: Optional[str] = None voice: Optional[GrokVoice] = "Ara" - turn_detection: Optional[TurnDetection] = None + turn_detection: Optional[TurnDetection] = Field( + default_factory=lambda: TurnDetection(type="server_vad") + ) audio: Optional[AudioConfiguration] = None # Tools can be ToolsSchema when provided by user, or list of dicts for API tools: Optional[ToolsSchema | List[GrokTool]] = None @@ -629,6 +633,26 @@ class ResponseAudioDone(ServerEvent): item_id: str +class ResponseFunctionCallArgumentsDelta(ServerEvent): + """Event containing incremental function call arguments. + + Parameters: + type: Event type, always "response.function_call_arguments.delta". + response_id: ID of the response. + item_id: ID of the conversation item. + call_id: ID of the function call. + delta: Incremental function arguments as JSON. + previous_item_id: ID of the previous item, if any. + """ + + type: Literal["response.function_call_arguments.delta"] + response_id: Optional[str] = None + item_id: Optional[str] = None + call_id: str + delta: str + previous_item_id: Optional[str] = None + + class ResponseFunctionCallArgumentsDone(ServerEvent): """Event indicating function call arguments are complete. @@ -820,6 +844,7 @@ _server_event_types = { "response.output_audio_transcript.done": ResponseAudioTranscriptDone, "response.output_audio.delta": ResponseAudioDelta, "response.output_audio.done": ResponseAudioDone, + "response.function_call_arguments.delta": ResponseFunctionCallArgumentsDelta, "response.function_call_arguments.done": ResponseFunctionCallArgumentsDone, "response.done": ResponseDone, } diff --git a/src/pipecat/services/grok/realtime/llm.py b/src/pipecat/services/grok/realtime/llm.py index ec4f263bd..acbb3f83c 100644 --- a/src/pipecat/services/grok/realtime/llm.py +++ b/src/pipecat/services/grok/realtime/llm.py @@ -27,14 +27,12 @@ from pipecat.frames.frames import ( EndFrame, Frame, InputAudioRawFrame, - InterimTranscriptionFrame, InterruptionFrame, LLMContextFrame, LLMFullResponseEndFrame, LLMFullResponseStartFrame, LLMMessagesAppendFrame, LLMSetToolsFrame, - LLMTextFrame, LLMUpdateSettingsFrame, StartFrame, TranscriptionFrame, @@ -57,7 +55,6 @@ from pipecat.processors.aggregators.llm_response_universal import ( from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext from pipecat.processors.frame_processor import FrameDirection from pipecat.services.llm_service import FunctionCallFromLLM, LLMService -from pipecat.transcriptions.language import Language from pipecat.utils.time import time_now_iso8601 from . import events @@ -110,50 +107,36 @@ class GrokRealtimeLLMService(LLMService): self, *, api_key: str, - voice: events.GrokVoice = "Ara", base_url: str = "wss://api.x.ai/v1/realtime", session_properties: Optional[events.SessionProperties] = None, start_audio_paused: bool = False, - sample_rate: int = 24000, **kwargs, ): """Initialize the Grok Realtime Voice Agent LLM service. Args: api_key: xAI API key for authentication. - voice: Voice to use for responses. Options: Ara, Rex, Sal, Eve, Leo. - Defaults to "Ara". base_url: WebSocket base URL for the realtime API. Defaults to "wss://api.x.ai/v1/realtime". session_properties: Configuration properties for the realtime session. - If None, uses default SessionProperties with the specified voice. + If None, uses default SessionProperties with voice "Ara". + To set a different voice, configure it in session_properties: + + session_properties = events.SessionProperties(voice="Rex") + + Available voices: Ara, Rex, Sal, Eve, Leo. start_audio_paused: Whether to start with audio input paused. Defaults to False. - sample_rate: Audio sample rate in Hz. Supported: 8000, 16000, 21050, 24000, - 32000, 44100, 48000. Defaults to 24000. **kwargs: Additional arguments passed to parent LLMService. """ super().__init__(base_url=base_url, **kwargs) self.api_key = api_key self.base_url = base_url - self._sample_rate = sample_rate - self._voice = voice - # Initialize session_properties with voice and audio config - if session_properties: - self._session_properties = session_properties - # Ensure voice is set - if not self._session_properties.voice: - self._session_properties.voice = voice - else: - self._session_properties = events.SessionProperties( - voice=voice, - turn_detection=events.TurnDetection(type="server_vad"), - audio=events.AudioConfiguration( - input=events.AudioInput(format=events.PCMAudioFormat(rate=sample_rate)), - output=events.AudioOutput(format=events.PCMAudioFormat(rate=sample_rate)), - ), - ) + # Initialize session_properties + self._session_properties: events.SessionProperties = ( + session_properties or events.SessionProperties() + ) self._audio_input_paused = start_audio_paused self._websocket = None @@ -192,6 +175,50 @@ class GrokRealtimeLLMService(LLMService): """ self._audio_input_paused = paused + def _get_configured_sample_rate(self, direction: str) -> Optional[int]: + """Get manually configured sample rate for input or output. + + Args: + direction: Either "input" or "output". + + Returns: + Configured sample rate or None if not manually configured. + For PCMU/PCMA formats, returns 8000 Hz (G.711 standard). + """ + if not self._session_properties.audio: + return None + + audio_config = ( + self._session_properties.audio.input + if direction == "input" + else self._session_properties.audio.output + ) + + if audio_config and audio_config.format: + # PCM format has configurable rate + if hasattr(audio_config.format, "rate"): + return audio_config.format.rate + # PCMU/PCMA formats are fixed at 8000 Hz (G.711 standard) + elif audio_config.format.type in ("audio/pcmu", "audio/pcma"): + return 8000 + + return None + + def _get_output_sample_rate(self) -> int: + """Get the output sample rate from session properties. + + Returns: + Output sample rate in Hz. + + Note: + This assumes start() has been called, which guarantees + session_properties.audio.output exists. + """ + rate = self._get_configured_sample_rate("output") + if rate is None: + raise RuntimeError("Output sample rate not configured.") + return rate + def _is_turn_detection_enabled(self) -> bool: """Check if server-side VAD is enabled.""" if self._session_properties.turn_detection: @@ -230,7 +257,7 @@ class GrokRealtimeLLMService(LLMService): ) -> int: """Calculate audio duration in milliseconds based on PCM audio parameters.""" if sample_rate is None: - sample_rate = self._sample_rate + sample_rate = self._get_output_sample_rate() samples = total_bytes / bytes_per_sample duration_seconds = samples / sample_rate return int(duration_seconds * 1000) @@ -260,6 +287,23 @@ class GrokRealtimeLLMService(LLMService): frame: The start frame triggering service initialization. """ await super().start(frame) + + # Ensure audio configuration exists with both input and output + if not self._session_properties.audio: + self._session_properties.audio = events.AudioConfiguration() + + # Fill in missing input configuration + if not self._session_properties.audio.input: + self._session_properties.audio.input = events.AudioInput( + format=events.PCMAudioFormat(rate=frame.audio_in_sample_rate) + ) + + # Fill in missing output configuration + if not self._session_properties.audio.output: + self._session_properties.audio.output = events.AudioOutput( + format=events.PCMAudioFormat(rate=frame.audio_out_sample_rate) + ) + await self._connect() async def stop(self, frame: EndFrame): @@ -501,7 +545,7 @@ class GrokRealtimeLLMService(LLMService): frame = TTSAudioRawFrame( audio=audio, - sample_rate=self._sample_rate, + sample_rate=self._get_output_sample_rate(), num_channels=1, ) await self.push_frame(frame)