sinapsis-speech 0.3.4__tar.gz → 0.3.5__tar.gz

{sinapsis_speech-0.3.4 → sinapsis_speech-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-speech
-Version: 0.3.4
+Version: 0.3.5
 Summary: Generate speech using various libraries.
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech

{sinapsis_speech-0.3.4 → sinapsis_speech-0.3.5}/packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_base.py

@@ -46,6 +46,8 @@ class ElevenLabsBase(Template, abc.ABC):
         Args:
             api_key (str): The API used key to authenticate with ElevenLabs' API.
             model (Literal): The model identifier to use for speech synthesis.
+            output_file_name (str | None): Optional name for saved audio file.
+                If not provided a random UUI will be used as file name. Defaults to None.
             output_format (OutputFormat): The output audio format and quality. Options include:
                 ["mp3_22050_32", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128",
                 "mp3_44100_192", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100", "ulaw_8000"]
@@ -70,10 +72,10 @@ class ElevenLabsBase(Template, abc.ABC):
             "eleven_english_sts_v2",
             "eleven_multilingual_sts_v2",
         ] = "eleven_turbo_v2_5"
+        output_file_name: str | None = None
         output_format: OutputFormat = "mp3_44100_128"
         output_folder: str = os.path.join(SINAPSIS_CACHE_DIR, "elevenlabs", "audios")
         stream: bool = False
-        file_name : str = str(uuid.uuid4())
         voice: VoiceId | VoiceName | Voice = None
         voice_settings: VoiceSettings = Field(default_factory=dict)  # type: ignore[arg-type]
 
@@ -98,9 +100,14 @@ class ElevenLabsBase(Template, abc.ABC):
     def synthesize_speech(self, input_data: list[Packet]) -> RESPONSE_TYPE:
         """Abstract method for ElevenLabs speech synthesis."""
 
-    def _save_audio(self, response: Iterator[bytes] | bytes, file_format: str) -> str:
+    def _save_audio(self, response: Iterator[bytes] | bytes, file_format: str, idx: int) -> str:
         """Saves the audio to a file and returns the file path."""
-        output_file = os.path.join(self.attributes.output_folder, f"{self.attributes.file_name}.{file_format}")
+        if self.attributes.output_file_name:
+            file_name = self.attributes.output_file_name + "_" + str(idx)
+        else:
+            file_name = uuid.uuid4()
+
+        output_file = os.path.join(self.attributes.output_folder, f"{file_name}.{file_format}")
         try:
             save(response, output_file)
             self.logger.info(f"Audio saved to: {output_file}")
@@ -132,13 +139,12 @@ class ElevenLabsBase(Template, abc.ABC):
             self.logger.error(f"Value error while processing audio chunks: {e}")
             raise
 
-    def _process_audio_output(self, response: Iterator[bytes] | bytes) -> str | IO[bytes]:
+    def _process_audio_output(self, idx: int, response: Iterator[bytes] | bytes) -> str | IO[bytes]:
         """Processes a single audio output (either stream or file)."""
         if self.attributes.stream:
             return self._generate_audio_stream(response)
-        else:
-            file_format = "mp3" if "mp3" in self.attributes.output_format else "wav"
-            return self._save_audio(response, file_format)
+        file_format = "mp3" if "mp3" in self.attributes.output_format else "wav"
+        return self._save_audio(response, file_format, idx)
 
     def generate_speech(self, input_data: list[Packet]) -> list[str | IO[bytes]] | None:
         """Generates speech and saves it to a file."""
@@ -149,7 +155,7 @@ class ElevenLabsBase(Template, abc.ABC):
         if isinstance(responses, Iterator):
             responses = [responses]
 
-        audio_outputs = [self._process_audio_output(response) for response in responses]
+        audio_outputs = [self._process_audio_output(idx, response) for idx, response in enumerate(responses)]
         return audio_outputs
 
     def _handle_streaming_output(self, audio_outputs: list[str | IO[bytes]]) -> list[AudioPacket]:

sinapsis_speech-0.3.5/packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_sts.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+"""Speech-To-Speech template for ElevenLabs"""
+
+from typing import Callable, Iterator, Literal
+
+from sinapsis_core.data_containers.data_packet import AudioPacket
+
+from sinapsis_elevenlabs.helpers.voice_utils import create_voice_settings, get_voice_id
+from sinapsis_elevenlabs.templates.elevenlabs_base import ElevenLabsBase
+
+
+class ElevenLabsSTS(ElevenLabsBase):
+    """Template to interact with ElevenLabs speech-to-speech API."""
+
+    PACKET_TYPE_NAME: str = "audios"
+
+    class AttributesBaseModel(ElevenLabsBase.AttributesBaseModel):
+        """Attributes specific to ElevenLabs STS API interaction.
+
+        This class overrides the base attributes of `ElevenLabsBase` to define
+        default models specific to the ElevenLabs STS system.
+        """
+
+        model: Literal["eleven_english_sts_v2", "eleven_multilingual_sts_v2"] = "eleven_multilingual_sts_v2"
+
+    def synthesize_speech(self, input_data: list[AudioPacket]) -> Iterator[bytes]:
+        """
+        Sends an audio input to the ElevenLabs API for speech-to-speech synthesis.
+
+        This method processes the provided audio input using the specified voice, model,
+        and settings to generate a new audio response.
+        """
+
+        try:
+            method: Callable[..., Iterator[bytes]] = (
+                self.client.speech_to_speech.convert_as_stream
+                if self.attributes.stream
+                else self.client.speech_to_speech.convert
+            )
+            return method(
+                audio=input_data[0].content,
+                voice_id=get_voice_id(self.client, voice=self.attributes.voice),
+                model_id=self.attributes.model,
+                voice_settings=create_voice_settings(self.attributes.voice_settings),
+                output_format=self.attributes.output_format,
+                optimize_streaming_latency=str(self.attributes.streaming_latency),
+            )
+        except ValueError as e:
+            self.logger.error(f"Value error synthesizing speech: {e}")
+            raise
+        except TypeError as e:
+            self.logger.error(f"Type error in input data or parameters: {e}")
+            raise
+        except KeyError as e:
+            self.logger.error(f"Missing key in input data or settings: {e}")
+            raise

sinapsis_speech-0.3.5/packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_voice_clone.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+"""Text-To-Speech template for ElevenLabs"""
+
+from elevenlabs import Voice
+from sinapsis_core.data_containers.data_packet import AudioPacket, DataContainer
+
+from sinapsis_elevenlabs.templates.elevenlabs_tts import ElevenLabsTTS
+
+
+class ElevenLabsVoiceClone(ElevenLabsTTS):
+    """Template to clone a voice using ElevenLabs API."""
+
+    class AttributesBaseModel(ElevenLabsTTS.AttributesBaseModel):
+        """Attributes specific to the ElevenLabsVoiceClone class."""
+
+        name: str | None = None
+        description: str | None = None
+
+    def clone_voice(self, input_data: list[AudioPacket]) -> Voice:
+        """Clones a voice using the provided audio files."""
+        files = [f.content for f in input_data]
+        try:
+            add_voice_response = self.client.voices.add(
+                name=self.attributes.name,
+                description=self.attributes.description,
+                files=files,
+            )
+            cloned_voice = self.client.voices.get(add_voice_response.voice_id)
+            self.logger.info(f"Voice cloned successfully: {cloned_voice.name}")
+            return cloned_voice
+        except ValueError as e:
+            self.logger.error(f"Value error in input data or parameters: {e}")
+            raise
+        except TypeError as e:
+            self.logger.error(f"Type error with input data or files: {e}")
+            raise
+        except KeyError as e:
+            self.logger.error(f"Missing expected key in API response: {e}")
+            raise
+
+    def execute(self, container: DataContainer) -> DataContainer:
+        """Executes the voice cloning process and generates the speech output."""
+        audios = getattr(container, "audios", None)
+        if not audios:
+            self.logger.debug("No audios provided to clone voice")
+            return container
+        self.attributes.voice = self.clone_voice(audios)
+
+        container = super().execute(container)
+
+        return container

{sinapsis_speech-0.3.4 → sinapsis_speech-0.3.5}/packages/sinapsis_speech.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-speech
-Version: 0.3.4
+Version: 0.3.5
 Summary: Generate speech using various libraries.
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech

{sinapsis_speech-0.3.4 → sinapsis_speech-0.3.5}/packages/sinapsis_speech.egg-info/SOURCES.txt

@@ -7,7 +7,9 @@ packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/helpers/env_var_keys.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/helpers/voice_utils.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/__init__.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_base.py
+packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_sts.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_tts.py
+packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_voice_clone.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/templates/elevenlabs_voice_generation.py
 packages/sinapsis_f5_tts/src/sinapsis_f5_tts/__init__.py
 packages/sinapsis_f5_tts/src/sinapsis_f5_tts/templates/__init__.py

{sinapsis_speech-0.3.4 → sinapsis_speech-0.3.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sinapsis-speech"
-version = "0.3.4"
+version = "0.3.5"
 description = "Generate speech using various libraries."
 authors = [
     {name = "SinapsisAI", email = "dev@sinapsis.tech"},