sinapsis-speech 0.4.5__tar.gz → 0.5.0__tar.gz

{sinapsis_speech-0.4.5/packages/sinapsis_speech.egg-info → sinapsis_speech-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-speech
-Version: 0.4.5
+Version: 0.5.0
 Summary: Generate speech using various libraries.
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech
@@ -20,6 +20,7 @@ Requires-Dist: sinapsis-speech[gradio-app]; extra == "all"
 Requires-Dist: sinapsis-zonos[all]; extra == "all"
 Requires-Dist: sinapsis-parakeet-tdt[all]; extra == "all"
 Requires-Dist: sinapsis-orpheus-cpp[all]; extra == "all"
+Requires-Dist: sinapsis-csm[all]; extra == "all"
 Provides-Extra: gradio-app
 Requires-Dist: sinapsis[webapp]>=0.2.3; extra == "gradio-app"
 Dynamic: license-file
@@ -61,6 +62,7 @@ This repo includes packages for performing speech synthesis using different tool
 * <code>sinapsis-zonos</code>
 * <code>sinapsis-orpheus-cpp</code>
 * <code>sinapsis-parakeet</code>
+* <code>sinapsis-csm</code>
 
 Install using your preferred package manager. We strongly recommend using <code>uv</code>. To install <code>uv</code>, refer to the [official documentation](https://docs.astral.sh/uv/getting-started/installation/#installation-methods).
 
@@ -176,6 +178,17 @@ For specific instructions and further details, see the [README.md](https://githu
 
 </details>
 
+<details>
+<summary id="parakeet-tdt"><strong><span style="font-size: 1.4em;"> Sinapsis Parakeet-TDT</span></strong></summary>
+
+This package provides a template for seamlessly integrating, configuring, and running **speech-to-text (STT)** functionalities powered by [SesameAILabs CSM](https://github.com/SesameAILabs/csm/tree/main?tab=readme-ov-file).
+
+- **CSMTTS**: Converts text into speech using the CSM model. This template processes text packets from the input container and adds the resulting audio packets to the container.
+
+For specific instructions and further details, see the [README.md](https://github.com/Sinapsis-AI/sinapsis-speech/blob/main/packages/sinapsis_csm/README.md).
+
+</details>
+
 <h2 id="webapp">🌐 Webapps</h2>
 The webapps included in this project showcase the modularity of the templates, in this case for speech generation tasks.
 
@@ -200,6 +213,9 @@ cd sinapsis-speech
 > [!IMPORTANT]
 > F5-TTS requires a reference audio file for voice cloning. Make sure you have a reference audio file in the artifacts directory.
 
+> [!IMPORTANT]
+> CSM requires an HF_TOKEN to run any inference. See the [official instructions](https://huggingface.co/docs/hub/security-tokens) and set it using <code>export HF_TOKEN="token-provided-by-hf"</code>
+
 > [!NOTE]
 > Agent configuration can be changed through the `AGENT_CONFIG_PATH` env var. You can check the available configurations in each package configs folder.
 
@@ -246,6 +262,11 @@ docker compose -f docker/compose_apps.yaml up -d sinapsis-orpheus-tts
 docker compose -f docker/compose_apps.yaml up -d sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+
 3. **Check the logs**
 
 - For ElevenLabs:
@@ -276,6 +297,11 @@ docker logs -f sinapsis-orpheus-tts
 docker logs -f sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker logs -f sinapsis-csm
+```
+
 4. **The logs will display the URL to access the webapp, e.g.,:**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860
@@ -335,6 +361,12 @@ uv run webapps/packet_tts_apps/kokoro_tts_app.py
 ```bash
 uv run webapps/generic_tts_apps/zonos_tts_app.py
 ```
+
+- For CSM:
+```bash
+uv run webapps/generic_tts_apps/csm_tts_app.py
+```
+
 4. **The terminal will display the URL to access the webapp (e.g.)**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0}/README.md

@@ -35,6 +35,7 @@ This repo includes packages for performing speech synthesis using different tool
 * <code>sinapsis-zonos</code>
 * <code>sinapsis-orpheus-cpp</code>
 * <code>sinapsis-parakeet</code>
+* <code>sinapsis-csm</code>
 
 Install using your preferred package manager. We strongly recommend using <code>uv</code>. To install <code>uv</code>, refer to the [official documentation](https://docs.astral.sh/uv/getting-started/installation/#installation-methods).
 
@@ -150,6 +151,17 @@ For specific instructions and further details, see the [README.md](https://githu
 
 </details>
 
+<details>
+<summary id="parakeet-tdt"><strong><span style="font-size: 1.4em;"> Sinapsis Parakeet-TDT</span></strong></summary>
+
+This package provides a template for seamlessly integrating, configuring, and running **speech-to-text (STT)** functionalities powered by [SesameAILabs CSM](https://github.com/SesameAILabs/csm/tree/main?tab=readme-ov-file).
+
+- **CSMTTS**: Converts text into speech using the CSM model. This template processes text packets from the input container and adds the resulting audio packets to the container.
+
+For specific instructions and further details, see the [README.md](https://github.com/Sinapsis-AI/sinapsis-speech/blob/main/packages/sinapsis_csm/README.md).
+
+</details>
+
 <h2 id="webapp">🌐 Webapps</h2>
 The webapps included in this project showcase the modularity of the templates, in this case for speech generation tasks.
 
@@ -174,6 +186,9 @@ cd sinapsis-speech
 > [!IMPORTANT]
 > F5-TTS requires a reference audio file for voice cloning. Make sure you have a reference audio file in the artifacts directory.
 
+> [!IMPORTANT]
+> CSM requires an HF_TOKEN to run any inference. See the [official instructions](https://huggingface.co/docs/hub/security-tokens) and set it using <code>export HF_TOKEN="token-provided-by-hf"</code>
+
 > [!NOTE]
 > Agent configuration can be changed through the `AGENT_CONFIG_PATH` env var. You can check the available configurations in each package configs folder.
 
@@ -220,6 +235,11 @@ docker compose -f docker/compose_apps.yaml up -d sinapsis-orpheus-tts
 docker compose -f docker/compose_apps.yaml up -d sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+
 3. **Check the logs**
 
 - For ElevenLabs:
@@ -250,6 +270,11 @@ docker logs -f sinapsis-orpheus-tts
 docker logs -f sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker logs -f sinapsis-csm
+```
+
 4. **The logs will display the URL to access the webapp, e.g.,:**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860
@@ -309,6 +334,12 @@ uv run webapps/packet_tts_apps/kokoro_tts_app.py
 ```bash
 uv run webapps/generic_tts_apps/zonos_tts_app.py
 ```
+
+- For CSM:
+```bash
+uv run webapps/generic_tts_apps/csm_tts_app.py
+```
+
 4. **The terminal will display the URL to access the webapp (e.g.)**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860

sinapsis_speech-0.5.0/packages/sinapsis_csm/src/sinapsis_csm/helpers/generator.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+from typing import Literal
+
+import torch
+from csm.generator import Generator
+from csm.models import Model
+
+
+class CSMGenerator:
+    """
+    Wrapper around the CSM model providing a simple interface
+    for text-to-speech generation
+    """
+
+    def __init__(self, device: Literal["cpu", "cuda"] = "cpu", sample_rate: int = 24000) -> None:
+        self.device: str = device
+        self.sample_rate: int = sample_rate
+        self.model: Model = Model.from_pretrained("sesame/csm-1b")
+        self.model.to(device=device)
+        self.model.sample_rate = sample_rate
+        self.generator = Generator(self.model)
+
+    def generate(
+        self, text: str, speaker: int = 0, context: list[str] | None = None, max_audio_length_ms: int = 10000
+    ) -> torch.Tensor:
+        if context is None:
+            context = []
+        return self.generator.generate(
+            text=text,
+            speaker=speaker,
+            context=context,
+            max_audio_length_ms=max_audio_length_ms,
+        )
+
+
+def load_csm_1b(device: Literal["cpu", "cuda"] = "cpu", sample_rate: int = 24000) -> CSMGenerator:
+    """
+    Loads and configures the CSM TTS model.
+
+    Returns:
+        CSMGenerator: Model wrapper with ready-to-use generate method.
+    """
+    return CSMGenerator(device=device, sample_rate=sample_rate)

sinapsis_speech-0.5.0/packages/sinapsis_csm/src/sinapsis_csm/templates/__init__.py

@@ -0,0 +1,19 @@
+import importlib
+from typing import Callable
+from sinapsis_csm.templates.csm_tts import CSMTTS
+
+_root_lib_path = "sinapsis_csm.templates"
+_template_lookup = {
+    "CSMTTS": f"{_root_lib_path}.csm_tts",
+}
+
+def __getattr__(name: str) -> Callable:
+    if name in _template_lookup:
+        module = importlib.import_module(_template_lookup[name])
+        return getattr(module, name)
+    raise AttributeError(f"Template `{name}` not found in `{_root_lib_path}`.")
+
+
+__all__ = ["CSMTTS"]
+
+

sinapsis_speech-0.5.0/packages/sinapsis_csm/src/sinapsis_csm/templates/csm_tts.py

@@ -0,0 +1,88 @@
+from typing import Literal
+import torch
+from sinapsis_core.data_containers.data_packet import AudioPacket, DataContainer
+from sinapsis_core.template_base import Template
+from sinapsis_core.template_base.base_models import TemplateAttributes, TemplateAttributeType
+from sinapsis_csm.helpers.generator import load_csm_1b
+
+
+class CSMTTS(Template):
+    """
+    Sinapsis template for converting text into speech using the CSM TTS model.
+    """
+
+    class AttributesBaseModel(TemplateAttributes):  # type: ignore
+        """
+        Defines configurable attributes for the CSMTTS template.
+        """
+        speaker_id: int = 0
+        max_audio_length_ms: int = 10000
+        device: Literal["cuda", "cpu"] = "cpu"
+        context: list[str] | None = None
+        sample_rate_hz: int = 24000
+
+    def __init__(self, attributes: TemplateAttributeType) -> None:
+        """
+        Initializes the template and loads the CSM model.
+
+        Args:
+            attributes (TemplateAttributeType): User-defined attributes from YAML configuration.
+        """
+        super().__init__(attributes)
+        self.model = load_csm_1b(
+            device=self.attributes.device,
+            sample_rate=self.attributes.sample_rate_hz
+        )
+
+    def generate_audio(self, text: str) -> torch.Tensor:
+        """
+        Converts input text to audio using the CSM model.
+
+        Args:
+            text (str): Input text string.
+
+        Returns:
+            torch.Tensor: Audio waveform tensor.
+        """
+        context = self.attributes.context if self.attributes.context else []
+        return self.model.generate(
+            text=text,
+            speaker=self.attributes.speaker_id,
+            context=context,
+            max_audio_length_ms=self.attributes.max_audio_length_ms,
+        )
+
+    def generate_audio_packet(self, audio: torch.Tensor, source_text: str) -> AudioPacket:
+        """
+        Wraps a raw audio tensor into a sinapsis compatible audioPacket
+
+        Args:
+            audio (torch.Tensor): Audio waveform.
+            source_text (str): Original input text used for generation.
+
+        Returns:
+            AudioPacket: Encapsulated audio data with metadata.
+        """
+        audio_np = audio.cpu().numpy()
+        return AudioPacket(
+            content=audio_np,
+            sample_rate=self.attributes.sample_rate_hz,
+            generic_data={"source_text": source_text, "model": "CSM"}
+        )
+
+    def execute(self, container: DataContainer) -> DataContainer:
+        """
+        Main method executed by Sinapsis. Converts all text packets in the input container to audio.
+
+        Args:
+            container (DataContainer): Input container with text packets.
+
+        Returns:
+            DataContainer: Output container with generated audio packets.
+        """
+        for packet in container.texts:
+            audio = self.generate_audio(packet.content)
+            audio_packet = self.generate_audio_packet(audio, packet.content)
+            audio_packet.source = self.instance_name
+            container.audios.append(audio_packet)
+        return container

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0/packages/sinapsis_speech.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-speech
-Version: 0.4.5
+Version: 0.5.0
 Summary: Generate speech using various libraries.
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech
@@ -20,6 +20,7 @@ Requires-Dist: sinapsis-speech[gradio-app]; extra == "all"
 Requires-Dist: sinapsis-zonos[all]; extra == "all"
 Requires-Dist: sinapsis-parakeet-tdt[all]; extra == "all"
 Requires-Dist: sinapsis-orpheus-cpp[all]; extra == "all"
+Requires-Dist: sinapsis-csm[all]; extra == "all"
 Provides-Extra: gradio-app
 Requires-Dist: sinapsis[webapp]>=0.2.3; extra == "gradio-app"
 Dynamic: license-file
@@ -61,6 +62,7 @@ This repo includes packages for performing speech synthesis using different tool
 * <code>sinapsis-zonos</code>
 * <code>sinapsis-orpheus-cpp</code>
 * <code>sinapsis-parakeet</code>
+* <code>sinapsis-csm</code>
 
 Install using your preferred package manager. We strongly recommend using <code>uv</code>. To install <code>uv</code>, refer to the [official documentation](https://docs.astral.sh/uv/getting-started/installation/#installation-methods).
 
@@ -176,6 +178,17 @@ For specific instructions and further details, see the [README.md](https://githu
 
 </details>
 
+<details>
+<summary id="parakeet-tdt"><strong><span style="font-size: 1.4em;"> Sinapsis Parakeet-TDT</span></strong></summary>
+
+This package provides a template for seamlessly integrating, configuring, and running **speech-to-text (STT)** functionalities powered by [SesameAILabs CSM](https://github.com/SesameAILabs/csm/tree/main?tab=readme-ov-file).
+
+- **CSMTTS**: Converts text into speech using the CSM model. This template processes text packets from the input container and adds the resulting audio packets to the container.
+
+For specific instructions and further details, see the [README.md](https://github.com/Sinapsis-AI/sinapsis-speech/blob/main/packages/sinapsis_csm/README.md).
+
+</details>
+
 <h2 id="webapp">🌐 Webapps</h2>
 The webapps included in this project showcase the modularity of the templates, in this case for speech generation tasks.
 
@@ -200,6 +213,9 @@ cd sinapsis-speech
 > [!IMPORTANT]
 > F5-TTS requires a reference audio file for voice cloning. Make sure you have a reference audio file in the artifacts directory.
 
+> [!IMPORTANT]
+> CSM requires an HF_TOKEN to run any inference. See the [official instructions](https://huggingface.co/docs/hub/security-tokens) and set it using <code>export HF_TOKEN="token-provided-by-hf"</code>
+
 > [!NOTE]
 > Agent configuration can be changed through the `AGENT_CONFIG_PATH` env var. You can check the available configurations in each package configs folder.
 
@@ -246,6 +262,11 @@ docker compose -f docker/compose_apps.yaml up -d sinapsis-orpheus-tts
 docker compose -f docker/compose_apps.yaml up -d sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+
 3. **Check the logs**
 
 - For ElevenLabs:
@@ -276,6 +297,11 @@ docker logs -f sinapsis-orpheus-tts
 docker logs -f sinapsis-parakeet
 ```
 
+- For CSM:
+```bash
+docker logs -f sinapsis-csm
+```
+
 4. **The logs will display the URL to access the webapp, e.g.,:**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860
@@ -335,6 +361,12 @@ uv run webapps/packet_tts_apps/kokoro_tts_app.py
 ```bash
 uv run webapps/generic_tts_apps/zonos_tts_app.py
 ```
+
+- For CSM:
+```bash
+uv run webapps/generic_tts_apps/csm_tts_app.py
+```
+
 4. **The terminal will display the URL to access the webapp (e.g.)**:
 ```bash
 Running on local URL:  http://127.0.0.1:7860

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0}/packages/sinapsis_speech.egg-info/SOURCES.txt

@@ -1,6 +1,11 @@
 LICENSE
 README.md
 pyproject.toml
+packages/sinapsis_csm/__init__.py
+packages/sinapsis_csm/src/sinapsis_csm/__init__.py
+packages/sinapsis_csm/src/sinapsis_csm/helpers/generator.py
+packages/sinapsis_csm/src/sinapsis_csm/templates/__init__.py
+packages/sinapsis_csm/src/sinapsis_csm/templates/csm_tts.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/__init__.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/helpers/__init__.py
 packages/sinapsis_elevenlabs/src/sinapsis_elevenlabs/helpers/env_var_keys.py

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0}/packages/sinapsis_speech.egg-info/requires.txt

@@ -9,6 +9,7 @@ sinapsis-speech[gradio-app]
 sinapsis-zonos[all]
 sinapsis-parakeet-tdt[all]
 sinapsis-orpheus-cpp[all]
+sinapsis-csm[all]
 
 [gradio-app]
 sinapsis[webapp]>=0.2.3

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0}/packages/sinapsis_speech.egg-info/top_level.txt

@@ -1,3 +1,4 @@
+sinapsis_csm
 sinapsis_elevenlabs
 sinapsis_f5_tts
 sinapsis_kokoro

{sinapsis_speech-0.4.5 → sinapsis_speech-0.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sinapsis-speech"
-version = "0.4.5"
+version = "0.5.0"
 description = "Generate speech using various libraries."
 authors = [
     {name = "SinapsisAI", email = "dev@sinapsis.tech"},
@@ -28,6 +28,7 @@ all = [
     "sinapsis-zonos[all]",
     "sinapsis-parakeet-tdt[all]",
     "sinapsis-orpheus-cpp[all]",
+    "sinapsis-csm[all]",
 
 ]
 gradio-app = [
@@ -51,7 +52,7 @@ sinapsis-zonos = { workspace = true }
 sinapsis-speech = { workspace = true }
 sinapsis-parakeet-tdt = { workspace = true }
 sinapsis-orpheus-cpp = { workspace = true }
-sinapsis-chatterbox = { workspace = true }
+sinapsis-csm = { workspace = true }
 
 
 [[tool.uv.index]]