#53, #80

README.md

@@ -32,7 +32,7 @@ Check the [FAQ page](./FAQ.md) for answers to a lot of questions around the usag
 
 ## Updates
 
-Latest Version: v0.3.45
+Latest Version: v0.3.46
 
 See [release history](https://github.com/KoljaB/RealtimeTTS/releases).
 
@@ -308,6 +308,12 @@ When you initialize the `TextToAudioStream` class, you have various options to c
 - **Default**: en
 - **Description**: Language to use for sentence splitting.
 
+#### `muted` (bool)
+- **Type**: Bool
+- **Required**: No
+- **Default**: False
+- **Description**: Global muted parameter. If True, no pyAudio stream will be opened. Disables audio playback via local speakers (in case you want to synthesize to file or process audio chunks) and overrides the play parameters muted setting.
+
 #### `level` (int)
 - **Type**: Integer
 - **Required**: No

RealtimeTTS/stream_player.py

@@ -21,7 +21,8 @@ def __init__(
             format: int = pyaudio.paInt16,
             channels: int = 1,
             rate: int = 16000,
-            output_device_index=None):
+            output_device_index=None,
+            muted: bool = False):
         """
         Args:
             format (int): Audio format, defaults to pyaudio.paInt16
@@ -33,6 +34,7 @@ def __init__(
         self.channels = channels
         self.rate = rate
         self.output_device_index = output_device_index
+        self.muted = muted
 
 
 class AudioStream:
@@ -58,27 +60,33 @@ def open_stream(self):
         pySampleRate = self.config.rate
         pyOutput_device_index = self.config.output_device_index
 
-        if self.config.format == pyaudio.paCustomFormat:
-            pyFormat = self.pyaudio_instance.get_format_from_width(2)
-            logging.debug("Opening stream for mpeg audio chunks, "
-                          f"pyFormat: {pyFormat}, pyChannels: {pyChannels}, "
-                          f"pySampleRate: {pySampleRate}")
+        if self.config.muted:
+            print("Muted mode, no opening stream")
+            logging.debug("Muted mode, no opening stream")
+
         else:
-            pyFormat = self.config.format
-            logging.debug("Opening stream for wave audio chunks, "
-                          f"pyFormat: {pyFormat}, pyChannels: {pyChannels}, "
-                          f"pySampleRate: {pySampleRate}")
+            print("Opening stream")
+            if self.config.format == pyaudio.paCustomFormat:
+                pyFormat = self.pyaudio_instance.get_format_from_width(2)
+                logging.debug("Opening stream for mpeg audio chunks, "
+                            f"pyFormat: {pyFormat}, pyChannels: {pyChannels}, "
+                            f"pySampleRate: {pySampleRate}")
+            else:
+                pyFormat = self.config.format
+                logging.debug("Opening stream for wave audio chunks, "
+                            f"pyFormat: {pyFormat}, pyChannels: {pyChannels}, "
+                            f"pySampleRate: {pySampleRate}")
 
-        try:
-            self.stream = self.pyaudio_instance.open(
-                format=pyFormat,
-                channels=pyChannels,
-                rate=pySampleRate,
-                output_device_index=pyOutput_device_index,
-                output=True)
-        except Exception as e:
-            print(f"Error opening stream: {e}")
-            exit(0)
+            try:
+                self.stream = self.pyaudio_instance.open(
+                    format=pyFormat,
+                    channels=pyChannels,
+                    rate=pySampleRate,
+                    output_device_index=pyOutput_device_index,
+                    output=True)
+            except Exception as e:
+                print(f"Error opening stream: {e}")
+                exit(0)
 
     def start_stream(self):
         """Starts the audio stream."""
@@ -224,7 +232,6 @@ def _play_chunk(self, chunk):
         for i in range(0, len(chunk), sub_chunk_size):
             sub_chunk = chunk[i:i + sub_chunk_size]
 
-            # print("Playing/yielding chunk")
             if not self.first_chunk_played and self.on_playback_start:
                 self.on_playback_start()
                 self.first_chunk_played = True

RealtimeTTS/text_to_stream.py

@@ -29,6 +29,7 @@ def __init__(self,
                  output_device_index=None,
                  tokenizer: str = "nltk",
                  language: str = "en",
+                 muted: bool = False,
                  level=logging.WARNING,
                  ):
         """
@@ -53,6 +54,11 @@ def __init__(self,
             tokenizer (str, optional): Tokenizer to use for sentence splitting
                 (currently "nltk" and "stanza" are supported).
             language (str, optional): Language to use for sentence splitting.
+            muted (bool, optional): If True, disables audio playback via local
+                speakers (in case you want to synthesize to file or process
+                audio chunks). Default is False.
+                If set to True it will override the play parameters muted
+                setting.
             level (int, optional): Logging level. Defaults to logging.WARNING.
         """
         self.log_characters = log_characters
@@ -67,6 +73,7 @@ def __init__(self,
         self.abort_events = []
         self.tokenizer = tokenizer
         self.language = language
+        self.global_muted = muted
         self.player = None
         self.play_lock = threading.Lock()
         self.is_playing_flag = False
@@ -118,13 +125,16 @@ def load_engine(
 
         # Check if the engine doesn't support consuming generators directly
         if not self.engine.can_consume_generators:
+            config = AudioConfiguration(
+                format,
+                channels,
+                rate,
+                self.output_device_index,
+                muted=self.global_muted)
+
             self.player = StreamPlayer(
                 self.engine.queue,
-                AudioConfiguration(
-                    format,
-                    channels,
-                    rate,
-                    self.output_device_index),
+                config,
                 on_playback_start=self._on_audio_stream_start)
         else:
             self.engine.on_playback_start = self._on_audio_stream_start
@@ -231,6 +241,8 @@ def play(
             which the first sentence fragment is forced to be yielded.
             Default is 15 words.
         """
+        if self.global_muted:
+            muted = True
 
         if is_external_call:
             if not self.play_lock.acquire(blocking=False):
@@ -295,7 +307,11 @@ def play(
                 self.generated_text += self.char_iter.iterated_text
 
                 self._create_iterators()
-                self.is_playing_flag = False
+
+                if is_external_call:
+
+                    self.is_playing_flag = False
+                    self.play_lock.release()
         else:
             try:
                 # Start the audio player to handle playback

setup.py

@@ -9,7 +9,7 @@
 
 setuptools.setup(
     name="RealTimeTTS",
-    version="0.3.44",
+    version="0.3.46",
     author="Kolja Beigel",
     author_email="[email protected]",
     description="*Stream text into audio with an easy-to-use, highly configurable library delivering voice output with minimal latency.",