Allow speech-synthesis to be hosted externally

docs/genindex.html

@@ -349,6 +349,8 @@ <h2 id="C">C</h2>
       <li><a href="index.html#jarvis.modules.models.classes.BackgroundTask.check_empty_string">check_empty_string() (jarvis.modules.models.classes.BackgroundTask class method)</a>
 </li>
       <li><a href="index.html#jarvis.modules.audio.speech_synthesis.check_existing">check_existing() (in module jarvis.modules.audio.speech_synthesis)</a>
+</li>
+      <li><a href="index.html#jarvis.modules.audio.speech_synthesis.check_external">check_external() (in module jarvis.modules.audio.speech_synthesis)</a>
 </li>
       <li><a href="index.html#jarvis.modules.models.classes.BackgroundTask.check_hours_format">check_hours_format() (jarvis.modules.models.classes.BackgroundTask class method)</a>
 </li>
@@ -1038,7 +1040,7 @@ <h2 id="H">H</h2>
   <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="index.html#jarvis.executors.static_responses.hi">hi() (in module jarvis.executors.static_responses)</a>
 </li>
-      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.High_Quality">High_Quality (jarvis.modules.models.enums.SSQuality attribute)</a>
+      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.High">High (jarvis.modules.models.enums.SSQuality attribute)</a>
 </li>
       <li><a href="index.html#jarvis.modules.models.classes.EnvConfig.home">home (jarvis.modules.models.classes.EnvConfig attribute)</a>
 </li>
@@ -2121,7 +2123,7 @@ <h2 id="L">L</h2>
 </li>
       <li><a href="index.html#jarvis.modules.models.classes.Settings.logical_cores">logical_cores (jarvis.modules.models.classes.Settings attribute)</a>
 </li>
-      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.Low_Quality">Low_Quality (jarvis.modules.models.enums.SSQuality attribute)</a>
+      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.Low">Low (jarvis.modules.models.enums.SSQuality attribute)</a>
 </li>
       <li><a href="index.html#jarvis.executors.lights_squire.lumen">lumen() (in module jarvis.executors.lights_squire)</a>
 </li>
@@ -2159,7 +2161,7 @@ <h2 id="M">M</h2>
         <li><a href="index.html#jarvis.modules.dictionary.dictionary.meaning">(in module jarvis.modules.dictionary.dictionary)</a>
 </li>
       </ul></li>
-      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.Medium_Quality">Medium_Quality (jarvis.modules.models.enums.SSQuality attribute)</a>
+      <li><a href="index.html#jarvis.modules.models.enums.SSQuality.Medium">Medium (jarvis.modules.models.enums.SSQuality attribute)</a>
 </li>
       <li><a href="index.html#jarvis.modules.meetings.ics_meetings.meetings">meetings() (in module jarvis.modules.meetings.ics_meetings)</a>
 </li>
@@ -3005,10 +3007,12 @@ <h2 id="S">S</h2>
       <li><a href="index.html#jarvis.executors.volume.speaker_volume">speaker_volume() (in module jarvis.executors.volume)</a>
 </li>
       <li><a href="index.html#jarvis.modules.models.classes.EnvConfig.speech_rate">speech_rate (jarvis.modules.models.classes.EnvConfig attribute)</a>
+</li>
+      <li><a href="index.html#jarvis.api.routers.speech_synthesis.speech_synthesis">speech_synthesis() (in module jarvis.api.routers.speech_synthesis)</a>
 </li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="index.html#jarvis.api.routers.speech_synthesis.speech_synthesis">speech_synthesis() (in module jarvis.api.routers.speech_synthesis)</a>
+      <li><a href="index.html#jarvis.modules.models.classes.EnvConfig.speech_synthesis_api">speech_synthesis_api (jarvis.modules.models.classes.EnvConfig attribute)</a>
 </li>
       <li><a href="index.html#jarvis.modules.audio.speech_synthesis.speech_synthesis_api">speech_synthesis_api() (in module jarvis.modules.audio.speech_synthesis)</a>
 </li>

jarvis/api/routers/speech_synthesis.py

@@ -2,6 +2,7 @@
 from http import HTTPStatus
 from json import JSONDecodeError
 from threading import Thread
+from urllib.parse import urljoin
 
 import requests
 from fastapi import APIRouter
@@ -28,11 +29,13 @@ async def speech_synthesis_voices():
         - 200: If call to speech synthesis endpoint was successful.
         - 500: If call to speech synthesis fails.
     """
+    if models.env.speech_synthesis_api:
+        url = urljoin(str(models.env.speech_synthesis_api), "/api/voices")
+    else:
+        # noinspection HttpUrlsUsage
+        url = f"http://{models.env.speech_synthesis_host}:{models.env.speech_synthesis_port}/api/voices"
     try:
-        response = requests.get(
-            url=f"http://{models.env.speech_synthesis_host}:{models.env.speech_synthesis_port}/api/voices",
-            timeout=3,
-        )
+        response = requests.get(url=url, timeout=3)
     except EgressErrors as error:
         logger.error(error)
         raise APIResponse(

jarvis/executors/car.py

@@ -1,5 +1,5 @@
 import time
-from datetime import datetime
+from datetime import UTC, datetime
 
 # noinspection PyProtectedMember
 from multiprocessing.context import TimeoutError as ThreadTimeoutError
@@ -378,7 +378,7 @@ def report(
         str:
         Response to the user.
     """
-    default_dt_string = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%S+0000")
+    default_dt_string = datetime.now(UTC).strftime("%Y-%m-%dT%H:%M:%S+0000")
     report_time = convert_dt_report(
         dt_string=status_data.get("lastUpdatedTime", default_dt_string)
     )

jarvis/executors/files.py

@@ -71,12 +71,12 @@ def get_contacts() -> Dict[str, Dict[str, str]] | DefaultDict[str, Dict[str, str
 
 
 def get_frequent() -> Dict[str, int]:
-    """Support getting frequently used keywords' mapping file."""
+    """Retrieve frequently used keywords' mapping file."""
     return _loader(models.fileio.frequent, default={})
 
 
 def put_frequent(data: Dict[str, int]) -> None:
-    """Support writing frequently used keywords' mapping file.
+    """Writes frequently used keywords into a mapping file.
 
     Args:
         data: Takes the mapping dictionary as an argument.
@@ -96,12 +96,7 @@ def get_location() -> DefaultDict[str, Dict | float | bool]:
 
 
 def get_secure_send() -> Dict[str, Dict[str, Any]]:
-    """Get existing secure string information from the mapping file.
-
-    Returns:
-        Dict[str, Dict[str, Any]]:
-        Dictionary of secure send data.
-    """
+    """Get existing secure-send information from the mapping file."""
     return _loader(models.fileio.secure_send, default={})
 
 
@@ -136,22 +131,12 @@ def put_secure_send(data: Dict[str, Dict[str, Any]]) -> None:
 
 
 def get_custom_conditions() -> Dict[str, Dict[str, str]]:
-    """Custom conditions to map specific keywords to one or many functions.
-
-    Returns:
-        Dict[str, Dict[str, str]]:
-        A unique key value pair, of custom phrase as key and an embedded dict of function name and phrase.
-    """
+    """Custom conditions to map specific keywords to one or many functions."""
     return _loader(models.fileio.conditions)
 
 
 def get_restrictions() -> List[str]:
-    """Function level restrictions to restrict certain keywords via offline communicator.
-
-    Returns:
-        List[str]:
-        A list of function names that has to be restricted.
-    """
+    """Function level restrictions to restrict certain keywords via offline communicator."""
     return _loader(models.fileio.restrictions, default=[])
 
 
@@ -165,12 +150,7 @@ def put_restrictions(restrictions: List[str]) -> None:
 
 
 def get_gpt_data() -> List[Dict[str, str]]:
-    """Get history from Jarvis -> Ollama conversation.
-
-    Returns:
-        List[Dict[str, str]]:
-        A list of dictionaries with request and response key-value pairs.
-    """
+    """Get history from Jarvis -> Ollama conversation."""
     return _loader(models.fileio.gpt_data)
 
 
@@ -184,12 +164,7 @@ def put_gpt_data(data: List[Dict[str, str]]) -> None:
 
 
 def get_automation() -> Dict[str, List[Dict[str, str | bool]] | Dict[str, str | bool]]:
-    """Load automation data from feed file.
-
-    Returns:
-        Dict[str, List[Dict[str, str | bool]] | Dict[str, str | bool]]:
-        Returns the automation data in the feed file.
-    """
+    """Load automation data from feed file."""
     return _loader(models.fileio.automation, default={})
 
 
@@ -216,12 +191,7 @@ def put_automation(
 
 
 def get_smart_devices() -> dict | bool | None:
-    """Load smart devices' data from feed file.
-
-    Returns:
-        dict | bool | None:
-        Returns the smart devices' data in the feed file.
-    """
+    """Load smart devices' data from feed file."""
     # fixme: Change the logic to NOT look for False specifically
     try:
         with open(models.fileio.smart_devices) as file:
@@ -248,22 +218,12 @@ def put_smart_devices(data: dict) -> None:
 
 
 def get_processes() -> Dict[str, List[int | List[str]]]:
-    """Get the processes' mapping from stored map file.
-
-    Returns:
-        Dict[str, List[int | List[str]]]:
-        Processes' mapping data.
-    """
+    """Get the processes' mapping from stored map file."""
     return _loader(models.fileio.processes, default={})
 
 
 def get_reminders() -> List[Dict[str, str]]:
-    """Get all reminders stored.
-
-    Returns:
-        List[Dict[str, str]]:
-        Returns a list of dictionary of information for stored reminders.
-    """
+    """Get all reminders stored."""
     return _loader(models.fileio.reminders, default=[])
 
 
@@ -277,12 +237,7 @@ def put_reminders(data: List[Dict[str, str]]) -> None:
 
 
 def get_alarms() -> List[Dict[str, str | bool]]:
-    """Get all alarms stored.
-
-    Returns:
-        Dict[str, str | bool]:
-        Returns a dictionary of information for stored alarms.
-    """
+    """Get all alarms stored."""
     return _loader(models.fileio.alarms, default=[])
 
 
@@ -296,12 +251,7 @@ def put_alarms(data: List[Dict[str, str | bool]]) -> None:
 
 
 def get_recognizer() -> classes.RecognizerSettings:
-    """Get the stored settings for speech recognition.
-
-    Returns:
-        RecognizerSettings:
-        Returns the parsed recognizer settings or default.
-    """
+    """Get the stored settings for speech recognition."""
     try:
         rec_data = _loader(models.fileio.recognizer, default={})
         return classes.RecognizerSettings(**rec_data)
@@ -311,12 +261,7 @@ def get_recognizer() -> classes.RecognizerSettings:
 
 
 def get_crontab() -> List[str]:
-    """Get the stored crontab settings.
-
-    Returns:
-        List[str]:
-        List of crontab entries.
-    """
+    """Get list of stored crontab settings."""
     try:
         data = _loader(models.fileio.crontab, default=[])
         assert isinstance(data, list)
@@ -329,20 +274,15 @@ def get_crontab() -> List[str]:
 
 
 def get_ip_info() -> Dict[str, Any]:
-    """Get IP information from a stored yaml file.
-
-    Returns:
-        Dict[str, Any]:
-        Returns the public IP info.
-    """
+    """Get IP information from a stored yaml file."""
     return _loader(models.fileio.ip_info, default={})
 
 
 def put_ip_info(data: Dict[str, Any]) -> None:
     """Store IP address information in a mapping file.
 
     Args:
-        data: Data to store.
+        data: IP information to be stored.
     """
     data["timestamp"] = int(time.time())
     if not data.get("loc") and data.get("lat") and data.get("lon"):

jarvis/modules/audio/speaker.py

@@ -9,6 +9,7 @@
 import sys
 from datetime import datetime
 from threading import Thread
+from urllib.parse import urljoin
 
 import pynotification
 import requests
@@ -54,8 +55,13 @@ def speech_synthesizer(
     text = text.replace("\N{DEGREE SIGN}F", " degrees fahrenheit")
     text = text.replace("\N{DEGREE SIGN}C", " degrees celsius")
     try:
+        if models.env.speech_synthesis_api:
+            url = urljoin(str(models.env.speech_synthesis_api), "/api/tts")
+        else:
+            # noinspection HttpUrlsUsage
+            url = f"http://{models.env.speech_synthesis_host}:{models.env.speech_synthesis_port}/api/tts"
         response = requests.post(
-            url=f"http://{models.env.speech_synthesis_host}:{models.env.speech_synthesis_port}/api/tts",
+            url=url,
             headers={"Content-Type": "text/plain"},
             params={"voice": voice, "vocoder": quality},
             data=text,
@@ -68,13 +74,7 @@ def speech_synthesizer(
                 file.write(response.content)
                 file.flush()
             return True
-        logger.error(
-            "{code}::http://{host}:{port}/api/tts".format(
-                code=response.status_code,
-                host=models.env.speech_synthesis_host,
-                port=models.env.speech_synthesis_port,
-            )
-        )
+        logger.error("%s::%s", response.status_code, url)
         return False
     except UnicodeError as error:
         logger.error(error)

jarvis/modules/audio/speech_synthesis.py

@@ -58,6 +58,22 @@ def find_pid_by_port(port: int) -> int:
             logger.error(error)
 
 
+def check_external() -> bool:
+    """Checks for speech synthesis API running externally.
+
+    Returns:
+        bool:
+        A boolean flag to indicate API usability.
+    """
+    if models.env.speech_synthesis_api:
+        try:
+            response = requests.get(models.env.speech_synthesis_api)
+            response.raise_for_status()
+            return True
+        except EgressErrors as error:
+            logger.error(error)
+
+
 def check_existing() -> bool:
     """Checks for existing connection.
 
@@ -245,6 +261,9 @@ def speech_synthesis_api() -> None:
     except DockerException as error:
         logger.critical(error.__str__())
         return
+    if check_external():
+        logger.info("Speech synthesis API is running externally. Connection validated.")
+        return
     if check_existing():  # Test call to speech synthesis API successful
         # Map existing API session with docker
         if container_id := run_existing_container(docker_client, True):

jarvis/modules/models/classes.py

@@ -352,9 +352,10 @@ class EnvConfig(BaseSettings):
     # Speech synthesis config (disabled for speaker by default)
     speech_synthesis_timeout: int = 0
     speech_synthesis_voice: str = "en-us_northern_english_male-glow_tts"
-    speech_synthesis_quality: enums.SSQuality = enums.SSQuality.Medium_Quality
+    speech_synthesis_quality: enums.SSQuality = enums.SSQuality.Medium
     speech_synthesis_host: str = socket.gethostbyname("localhost")
     speech_synthesis_port: PositiveInt = 5002
+    speech_synthesis_api: HttpUrl | None = None
 
     # Background tasks
     weather_alert: str | datetime | None = None

jarvis/modules/models/enums.py

@@ -83,6 +83,6 @@ class SSQuality(StrEnum):
 
     """
 
-    High_Quality = "high"
-    Medium_Quality = "medium"
-    Low_Quality = "low"
+    High = "high"
+    Medium = "medium"
+    Low = "low"