303 lines
12 KiB
Python
303 lines
12 KiB
Python
"""Voice satellite protocol."""
|
|
|
|
import logging
|
|
import time
|
|
from collections.abc import Iterable
|
|
from typing import Dict, Optional, Set, Union
|
|
|
|
# pylint: disable=no-name-in-module
|
|
from aioesphomeapi.api_pb2 import ( # type: ignore[attr-defined]
|
|
DeviceInfoRequest,
|
|
DeviceInfoResponse,
|
|
ListEntitiesDoneResponse,
|
|
ListEntitiesRequest,
|
|
MediaPlayerCommandRequest,
|
|
SubscribeHomeAssistantStatesRequest,
|
|
VoiceAssistantAnnounceFinished,
|
|
VoiceAssistantAnnounceRequest,
|
|
VoiceAssistantAudio,
|
|
VoiceAssistantConfigurationRequest,
|
|
VoiceAssistantConfigurationResponse,
|
|
VoiceAssistantEventResponse,
|
|
VoiceAssistantRequest,
|
|
VoiceAssistantSetConfiguration,
|
|
VoiceAssistantTimerEventResponse,
|
|
VoiceAssistantWakeWord,
|
|
)
|
|
from aioesphomeapi.model import (
|
|
VoiceAssistantEventType,
|
|
VoiceAssistantFeature,
|
|
VoiceAssistantTimerEventType,
|
|
)
|
|
from google.protobuf import message
|
|
|
|
from .api_server import APIServer
|
|
from .entity import MediaPlayerEntity
|
|
from .microwakeword import MicroWakeWord
|
|
from .models import ServerState
|
|
from .openwakeword import OpenWakeWord
|
|
from .util import call_all
|
|
|
|
_LOGGER = logging.getLogger(__name__)
|
|
|
|
|
|
class VoiceSatelliteProtocol(APIServer):
|
|
def __init__(self, state: ServerState) -> None:
|
|
super().__init__(state.name)
|
|
|
|
self.state = state
|
|
self.state.satellite = self
|
|
|
|
if self.state.media_player_entity is None:
|
|
self.state.media_player_entity = MediaPlayerEntity(
|
|
server=self,
|
|
state=state,
|
|
key=len(state.entities),
|
|
name="Media Player",
|
|
object_id="linux_voice_assistant_media_player",
|
|
music_player=state.music_player,
|
|
announce_player=state.tts_player,
|
|
)
|
|
self.state.entities.append(self.state.media_player_entity)
|
|
|
|
self._is_streaming_audio = False
|
|
self._tts_url: Optional[str] = None
|
|
self._tts_played = False
|
|
self._continue_conversation = False
|
|
self._timer_finished = False
|
|
self._is_speaking = False
|
|
self._run_finished = False
|
|
|
|
def handle_voice_event(
|
|
self, event_type: VoiceAssistantEventType, data: Dict[str, str]
|
|
) -> None:
|
|
_LOGGER.debug("Voice event: type=%s, data=%s", event_type.name, data)
|
|
|
|
if event_type == VoiceAssistantEventType.VOICE_ASSISTANT_RUN_START:
|
|
self._tts_url = data.get("url")
|
|
self._tts_played = False
|
|
self._continue_conversation = False
|
|
self._run_finished = False
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_STT_START:
|
|
self.state.event_bus.publish("voice_stt_start", data)
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_STT_VAD_START:
|
|
self.state.event_bus.publish("voice_vad_start", data)
|
|
elif event_type in (
|
|
VoiceAssistantEventType.VOICE_ASSISTANT_STT_VAD_END,
|
|
VoiceAssistantEventType.VOICE_ASSISTANT_STT_END,
|
|
):
|
|
self.state.event_bus.publish("voice_stt_end", data)
|
|
self._is_streaming_audio = False
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_INTENT_PROGRESS:
|
|
if data.get("tts_start_streaming") == "1":
|
|
self.play_tts()
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_INTENT_END:
|
|
if data.get("continue_conversation") == "1":
|
|
self._continue_conversation = True
|
|
# --- MODIFIED: Removed TTS_START handler from here ---
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_TTS_END:
|
|
self._tts_url = data.get("url")
|
|
self.play_tts()
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_RUN_END:
|
|
self._run_finished = True
|
|
if not self._is_speaking:
|
|
self._determine_final_state()
|
|
|
|
elif event_type == VoiceAssistantEventType.VOICE_ASSISTANT_ERROR:
|
|
self.state.event_bus.publish("voice_error", data)
|
|
self._determine_final_state()
|
|
|
|
def handle_timer_event(
|
|
self,
|
|
event_type: VoiceAssistantTimerEventType,
|
|
msg: VoiceAssistantTimerEventResponse,
|
|
) -> None:
|
|
_LOGGER.debug("Timer event: type=%s", event_type.name)
|
|
if event_type == VoiceAssistantTimerEventType.VOICE_ASSISTANT_TIMER_FINISHED:
|
|
if not self._timer_finished:
|
|
self.state.stop_word.is_active = True
|
|
self._timer_finished = True
|
|
self.duck()
|
|
self._play_timer_finished()
|
|
|
|
def handle_message(self, msg: message.Message) -> Iterable[message.Message]:
|
|
if isinstance(msg, VoiceAssistantEventResponse):
|
|
data: Dict[str, str] = {}
|
|
for arg in msg.data:
|
|
data[arg.name] = arg.value
|
|
self.handle_voice_event(VoiceAssistantEventType(msg.event_type), data)
|
|
elif isinstance(msg, VoiceAssistantAnnounceRequest):
|
|
_LOGGER.debug("Announcing: %s", msg.text)
|
|
assert self.state.media_player_entity is not None
|
|
urls = []
|
|
if msg.preannounce_media_id:
|
|
urls.append(msg.preannounce_media_id)
|
|
urls.append(msg.media_id)
|
|
self.state.stop_word.is_active = True
|
|
self._continue_conversation = msg.start_conversation
|
|
self.duck()
|
|
yield from self.state.media_player_entity.play(
|
|
urls, announcement=True, done_callback=self._tts_finished
|
|
)
|
|
elif isinstance(msg, VoiceAssistantTimerEventResponse):
|
|
self.handle_timer_event(VoiceAssistantTimerEventType(msg.event_type), msg)
|
|
elif isinstance(msg, DeviceInfoRequest):
|
|
yield DeviceInfoResponse(
|
|
uses_password=False,
|
|
name=self.state.name,
|
|
mac_address=self.state.mac_address,
|
|
voice_assistant_feature_flags=(
|
|
VoiceAssistantFeature.VOICE_ASSISTANT
|
|
| VoiceAssistantFeature.API_AUDIO
|
|
| VoiceAssistantFeature.ANNOUNCE
|
|
| VoiceAssistantFeature.START_CONVERSATION
|
|
| VoiceAssistantFeature.TIMERS
|
|
),
|
|
)
|
|
elif isinstance(
|
|
msg,
|
|
(
|
|
ListEntitiesRequest,
|
|
SubscribeHomeAssistantStatesRequest,
|
|
MediaPlayerCommandRequest,
|
|
),
|
|
):
|
|
for entity in self.state.entities:
|
|
yield from entity.handle_message(msg)
|
|
|
|
if isinstance(msg, ListEntitiesRequest):
|
|
yield ListEntitiesDoneResponse()
|
|
elif isinstance(msg, VoiceAssistantConfigurationRequest):
|
|
yield VoiceAssistantConfigurationResponse(
|
|
available_wake_words=[
|
|
VoiceAssistantWakeWord(
|
|
id=ww.id,
|
|
wake_word=ww.wake_word,
|
|
trained_languages=ww.trained_languages,
|
|
)
|
|
for ww in self.state.available_wake_words.values()
|
|
],
|
|
active_wake_words=[
|
|
ww.id for ww in self.state.wake_words.values() if ww.is_active
|
|
],
|
|
max_active_wake_words=2,
|
|
)
|
|
_LOGGER.info("Connected to Home Assistant")
|
|
self.state.event_bus.publish("ha_connected")
|
|
elif isinstance(msg, VoiceAssistantSetConfiguration):
|
|
active_wake_words: Set[str] = set()
|
|
for wake_word_id in msg.active_wake_words:
|
|
if wake_word_id in self.state.wake_words:
|
|
active_wake_words.add(wake_word_id)
|
|
continue
|
|
model_info = self.state.available_wake_words.get(wake_word_id)
|
|
if not model_info:
|
|
continue
|
|
_LOGGER.debug("Loading wake word: %s", model_info.config_path)
|
|
self.state.wake_words[wake_word_id] = model_info.load(
|
|
self.state.libtensorflowlite_c_path
|
|
)
|
|
_LOGGER.info("Wake word set: %s", wake_word_id)
|
|
active_wake_words.add(wake_word_id)
|
|
break
|
|
for wake_word in self.state.wake_words.values():
|
|
wake_word.is_active = wake_word.id in active_wake_words
|
|
_LOGGER.debug("Active wake words: %s", active_wake_words)
|
|
self.state.preferences.active_wake_words = list(active_wake_words)
|
|
self.state.save_preferences()
|
|
self.state.wake_words_changed = True
|
|
|
|
def handle_audio(self, audio_chunk: bytes) -> None:
|
|
if not self._is_streaming_audio:
|
|
return
|
|
self.send_messages([VoiceAssistantAudio(data=audio_chunk)])
|
|
|
|
def wakeup(self, wake_word: Union[MicroWakeWord, OpenWakeWord]) -> None:
|
|
self.state.event_bus.publish("voice_wakeword")
|
|
if self._timer_finished:
|
|
self._timer_finished = False
|
|
self.state.tts_player.stop()
|
|
_LOGGER.debug("Stopping timer finished sound")
|
|
return
|
|
wake_word_phrase = wake_word.wake_word
|
|
_LOGGER.debug("Detected wake word: %s", wake_word_phrase)
|
|
self.send_messages(
|
|
[VoiceAssistantRequest(start=True, wake_word_phrase=wake_word_phrase)]
|
|
)
|
|
self.duck()
|
|
self._is_streaming_audio = True
|
|
self.state.tts_player.play(self.state.wakeup_sound)
|
|
|
|
def stop(self) -> None:
|
|
self.state.stop_word.is_active = False
|
|
self.state.tts_player.stop()
|
|
if self._timer_finished:
|
|
self._timer_finished = False
|
|
_LOGGER.debug("Stopping timer finished sound")
|
|
else:
|
|
_LOGGER.debug("TTS response stopped manually")
|
|
self._tts_finished()
|
|
|
|
# --- MODIFIED: Added event publish to sync with audio start ---
|
|
def play_tts(self) -> None:
|
|
if (not self._tts_url) or self._tts_played:
|
|
return
|
|
|
|
# Only publish the start event the first time we begin speaking
|
|
if not self._is_speaking:
|
|
self.state.event_bus.publish("voice_tts_start", {})
|
|
|
|
self._is_speaking = True
|
|
self._tts_played = True
|
|
_LOGGER.debug("Playing TTS response: %s", self._tts_url)
|
|
self.state.stop_word.is_active = True
|
|
self.state.tts_player.play(self._tts_url, done_callback=self._tts_finished)
|
|
|
|
def duck(self) -> None:
|
|
_LOGGER.debug("Ducking music")
|
|
self.state.music_player.duck()
|
|
|
|
def unduck(self) -> None:
|
|
_LOGGER.debug("Unducking music")
|
|
self.state.music_player.unduck()
|
|
|
|
def _determine_final_state(self) -> None:
|
|
"""Called when both TTS and the pipeline run are finished."""
|
|
self._is_streaming_audio = False
|
|
self.state.stop_word.is_active = False
|
|
|
|
if self._continue_conversation:
|
|
self.send_messages([VoiceAssistantRequest(start=True)])
|
|
self._is_streaming_audio = True
|
|
_LOGGER.debug("Continuing conversation")
|
|
self.state.event_bus.publish("voice_listen")
|
|
else:
|
|
self.unduck()
|
|
self.state.event_bus.publish("voice_run_end")
|
|
self.state.event_bus.publish("voice_idle")
|
|
|
|
_LOGGER.debug("Final state determined")
|
|
|
|
def _tts_finished(self) -> None:
|
|
self._is_speaking = False
|
|
self.send_messages([VoiceAssistantAnnounceFinished()])
|
|
_LOGGER.debug("TTS audio playback finished")
|
|
|
|
if self._run_finished:
|
|
self._determine_final_state()
|
|
|
|
def _play_timer_finished(self) -> None:
|
|
if not self._timer_finished:
|
|
self.unduck()
|
|
return
|
|
self.state.tts_player.play(
|
|
self.state.timer_finished_sound,
|
|
done_callback=lambda: call_all(
|
|
lambda: time.sleep(1.0), self._play_timer_finished
|
|
),
|
|
)
|
|
|
|
def connection_lost(self, exc):
|
|
super().connection_lost(exc)
|
|
_LOGGER.info("Disconnected from Home Assistant")
|