Merge pull request #22 from rhasspy/synesthesiam-20240808-mic-snd-info

Add support for remotely triggered pipelines

Author: synesthesiam

README.md

@@ -134,7 +134,17 @@ Describe available services.
             * `version` - version of the model (string, optional)
     * `satellite` - information about voice satellite (optional)
         * `area` - name of area where satellite is located (string, optional)
-        * `snd_format` - optimal audio output format of satellite (optional)
+        * `has_vad` - true if the end of voice commands will be detected locally (boolean, optional)
+        * `active_wake_words` - list of wake words that are actively being listend for (list of string, optional)
+        * `max_active_wake_words` - maximum number of local wake words that can be run simultaneously (number, optional)
+        * `supports_trigger` - true if satellite supports remotely-triggered pipelines
+    * `mic` - list of audio input services (optional)
+        * `mic_format` - audio input format (required)
+            * `rate` - sample rate in hertz (int, required)
+            * `width` - sample width in bytes (int, required)
+            * `channels` - number of channels (int, required)
+    * `snd` - list of audio output services (optional)
+        * `snd_format` - audio output format (required)
             * `rate` - sample rate in hertz (int, required)
             * `width` - sample width in bytes (int, required)
             * `channels` - number of channels (int, required)
@@ -222,19 +232,48 @@ Play audio stream.
 Control of one or more remote voice satellites connected to a central server.
 
 * `run-satellite` - informs satellite that server is ready to run pipelines
-    * `start_stage` - request pipelines with a specific starting stage (string, optional)
 * `pause-satellite` - informs satellite that server is not ready anymore to run pipelines
 * `satellite-connected` - satellite has connected to the server
 * `satellite-disconnected` - satellite has been disconnected from the server
 * `streaming-started` - satellite has started streaming audio to the server
 * `streaming-stopped` - satellite has stopped streaming audio to the server
 
+Pipelines are run on the server, but can be triggered remotely from the server as well.
+
+* `run-pipeline` - runs a pipeline on the server or asks the satellite to run it when possible
+    * `start_stage` - pipeline stage to start at (string, required)
+    * `end_stage` - pipeline stage to end at (string, required)
+    * `wake_word_name` - name of detected wake word that started this pipeline (string, optional)
+        * From client only
+    * `wake_word_names` - names of wake words to listen for (list of string, optional)
+        * From server only
+        * `start_stage` must be "wake"
+    * `announce_text` - text to speak on the satellite
+        * From server only
+        * `start_stage` must be "tts"
+    * `restart_on_end` - true if the server should re-run the pipeline after it ends (boolean, default is false)
+        * Only used for always-on streaming satellites
+
 ### Timers
 
 * `timer-started` - a new timer has started
+    * `id` - unique id of timer (string, required)
+    * `total_seconds` - number of seconds the timer should run for (int, required)
+    * `name` - user-provided name for timer (string, optional)
+    * `start_hours` - hours the timer should run for as spoken by user (int, optional)
+    * `start_minutes` - minutes the timer should run for as spoken by user (int, optional)
+    * `start_seconds` - seconds the timer should run for as spoken by user (int, optional)
+    * `command` - optional command that the server will execute when the timer is finished
+        * `text` - text of command to execute (string, required)
+        * `language` - language of the command (string, optional)
 * `timer-updated` - timer has been paused/resumed or time has been added/removed
+    * `id` - unique id of timer (string, required)
+    * `is_active` - true if timer is running, false if paused (bool, required)
+    * `total_seconds` - number of seconds that the timer should run for now (int, required)
 * `timer-cancelled` - timer was cancelled
+    * `id` - unique id of timer (string, required)
 * `timer-finished` - timer finished without being cancelled
+    * `id` - unique id of timer (string, required)
 
 ## Event Flow
 

script/package

@@ -8,4 +8,6 @@ _PROGRAM_DIR = _DIR.parent
 _VENV_DIR = _PROGRAM_DIR / ".venv"
 
 context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
-subprocess.check_call([context.env_exe, _PROGRAM_DIR / "setup.py", "bdist_wheel"])
+subprocess.check_call(
+    [context.env_exe, _PROGRAM_DIR / "setup.py", "bdist_wheel", "sdist"]
+)

wyoming/VERSION

@@ -1 +1 @@
-1.5.4
+1.6.0

wyoming/info.py

@@ -1,4 +1,5 @@
 """Information about available services, models, etc.."""
+
 from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional
 
@@ -177,8 +178,39 @@ class Satellite(Artifact):
     area: Optional[str] = None
     """Name of the area the satellite is in."""
 
-    snd_format: Optional[AudioFormat] = None
-    """Format of the satellite's audio output."""
+    has_vad: Optional[bool] = None
+    """True if a local VAD will be used to detect the end of voice commands."""
+
+    active_wake_words: Optional[List[str]] = None
+    """Wake words that are currently being listened for."""
+
+    max_active_wake_words: Optional[int] = None
+    """Maximum number of local wake words that can be run simultaneously."""
+
+    supports_trigger: Optional[bool] = None
+    """Satellite supports remotely triggering pipeline runs."""
+
+
+# -----------------------------------------------------------------------------
+
+
+@dataclass
+class MicProgram(Artifact):
+    """Microphone information."""
+
+    mic_format: AudioFormat
+    """Input audio format."""
+
+
+# -----------------------------------------------------------------------------
+
+
+@dataclass
+class SndProgram(Artifact):
+    """Sound output information."""
+
+    snd_format: AudioFormat
+    """Output audio format."""
 
 
 # -----------------------------------------------------------------------------
@@ -203,6 +235,12 @@ class Info(Eventable):
     wake: List[WakeProgram] = field(default_factory=list)
     """Wake word detection services."""
 
+    mic: List[MicProgram] = field(default_factory=list)
+    """Audio input services."""
+
+    snd: List[SndProgram] = field(default_factory=list)
+    """Audio output services."""
+
     satellite: Optional[Satellite] = None
     """Satellite information."""
 
@@ -217,6 +255,8 @@ def event(self) -> Event:
             "handle": [p.to_dict() for p in self.handle],
             "intent": [p.to_dict() for p in self.intent],
             "wake": [p.to_dict() for p in self.wake],
+            "mic": [p.to_dict() for p in self.mic],
+            "snd": [p.to_dict() for p in self.snd],
         }
 
         if self.satellite is not None:
@@ -239,5 +279,7 @@ def from_event(event: Event) -> "Info":
             handle=[HandleProgram.from_dict(d) for d in event.data.get("handle", [])],
             intent=[IntentProgram.from_dict(d) for d in event.data.get("intent", [])],
             wake=[WakeProgram.from_dict(d) for d in event.data.get("wake", [])],
+            mic=[MicProgram.from_dict(d) for d in event.data.get("mic", [])],
+            snd=[SndProgram.from_dict(d) for d in event.data.get("snd", [])],
             satellite=satellite,
         )

wyoming/mic.py

@@ -10,7 +10,7 @@
 from .client import AsyncClient
 from .event import Event
 
-_LOGGER = logging.getLogger()
+_LOGGER = logging.getLogger(__name__)
 
 DOMAIN = "mic"
 

wyoming/pipeline.py

@@ -1,9 +1,9 @@
 """Pipeline events."""
+
 from dataclasses import dataclass
 from enum import Enum
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 
-from .audio import AudioFormat
 from .event import Event, Eventable
 
 _RUN_PIPELINE_TYPE = "run-pipeline"
@@ -38,14 +38,17 @@ class RunPipeline(Eventable):
     end_stage: PipelineStage
     """Stage to end the pipeline on."""
 
-    name: Optional[str] = None
-    """Name of pipeline to run"""
+    wake_word_name: Optional[str] = None
+    """Name of wake word that triggered this pipeline."""
 
     restart_on_end: bool = False
     """True if pipeline should restart automatically after ending."""
 
-    snd_format: Optional[AudioFormat] = None
-    """Desired format for audio output."""
+    wake_word_names: Optional[List[str]] = None
+    """Wake word names to listen for (start_stage = wake)."""
+
+    announce_text: Optional[str] = None
+    """Text to announce using text-to-speech (start_stage = tts)"""
 
     def __post_init__(self) -> None:
         start_valid = True
@@ -104,33 +107,26 @@ def event(self) -> Event:
             "restart_on_end": self.restart_on_end,
         }
 
-        if self.name is not None:
-            data["name"] = self.name
+        if self.wake_word_name is not None:
+            data["wake_word_name"] = self.wake_word_name
+
+        if self.wake_word_names:
+            data["wake_word_names"] = self.wake_word_names
 
-        if self.snd_format is not None:
-            data["snd_format"] = {
-                "rate": self.snd_format.rate,
-                "width": self.snd_format.width,
-                "channels": self.snd_format.channels,
-            }
+        if self.announce_text is not None:
+            data["announce_text"] = self.announce_text
 
         return Event(type=_RUN_PIPELINE_TYPE, data=data)
 
     @staticmethod
     def from_event(event: Event) -> "RunPipeline":
         assert event.data is not None
-        snd_format = event.data.get("snd_format")
 
         return RunPipeline(
             start_stage=PipelineStage(event.data["start_stage"]),
             end_stage=PipelineStage(event.data["end_stage"]),
-            name=event.data.get("name"),
+            wake_word_name=event.data.get("wake_word_name"),
             restart_on_end=event.data.get("restart_on_end", False),
-            snd_format=AudioFormat(
-                rate=snd_format["rate"],
-                width=snd_format["width"],
-                channels=snd_format["channels"],
-            )
-            if snd_format
-            else None,
+            wake_word_names=event.data.get("wake_word_names"),
+            announce_text=event.data.get("announce_text"),
         )

wyoming/satellite.py

@@ -1,9 +1,8 @@
 """Satellite events."""
+
 from dataclasses import dataclass
-from typing import Any, Dict, Optional
 
 from .event import Event, Eventable
-from .pipeline import PipelineStage
 
 _RUN_SATELLITE_TYPE = "run-satellite"
 _PAUSE_SATELLITE_TYPE = "pause-satellite"
@@ -17,28 +16,16 @@
 class RunSatellite(Eventable):
     """Informs the satellite that the server is ready to run a pipeline."""
 
-    start_stage: Optional[PipelineStage] = None
-
     @staticmethod
     def is_type(event_type: str) -> bool:
         return event_type == _RUN_SATELLITE_TYPE
 
     def event(self) -> Event:
-        data: Dict[str, Any] = {}
-
-        if self.start_stage is not None:
-            data["start_stage"] = self.start_stage.value
-
-        return Event(type=_RUN_SATELLITE_TYPE, data=data)
+        return Event(type=_RUN_SATELLITE_TYPE)
 
     @staticmethod
     def from_event(event: Event) -> "RunSatellite":
-        # note: older versions don't send event.data
-        start_stage = None
-        if value := (event.data or {}).get("start_stage"):
-            start_stage = PipelineStage(value)
-
-        return RunSatellite(start_stage=start_stage)
+        return RunSatellite()
 
 
 @dataclass

wyoming/snd.py

@@ -10,7 +10,7 @@
 from .client import AsyncClient
 from .event import Event, Eventable
 
-_LOGGER = logging.getLogger()
+_LOGGER = logging.getLogger(__name__)
 
 _PLAYED_TYPE = "played"
 

wyoming/wake.py

@@ -10,7 +10,7 @@
 from .client import AsyncClient
 from .event import Event, Eventable
 
-_LOGGER = logging.getLogger()
+_LOGGER = logging.getLogger(__name__)
 
 DOMAIN = "wake"
 _DETECTION_TYPE = "detection"

wyoming/zeroconf.py

@@ -4,7 +4,7 @@
 import socket
 from typing import Optional
 
-_LOGGER = logging.getLogger()
+_LOGGER = logging.getLogger(__name__)
 
 try:
     from zeroconf.asyncio import AsyncServiceInfo, AsyncZeroconf