sinapsis-csm 0.1.0__tar.gz

sinapsis_csm-0.1.0/PKG-INFO

@@ -0,0 +1,249 @@
+Metadata-Version: 2.4
+Name: sinapsis-csm
+Version: 0.1.0
+Summary: Text to speech using CSM TTS model
+Author-email: SinapsisAI <dev@sinapsis.tech>
+Project-URL: Homepage, https://sinapsis.tech
+Project-URL: Documentation, https://docs.sinapsis.tech/docs
+Project-URL: Tutorials, https://docs.sinapsis.tech/tutorials
+Project-URL: Repository, https://github.com/Sinapsis-AI/sinapsis-speech.git
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: silentcipher
+Requires-Dist: csm
+Provides-Extra: data-tools
+Requires-Dist: sinapsis-data-readers[all]>=0.1.2; extra == "data-tools"
+Requires-Dist: sinapsis-data-writers[soundfile]>=0.1.2; extra == "data-tools"
+Provides-Extra: all
+Requires-Dist: sinapsis-csm[data-tools]; extra == "all"
+
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis CSM
+<br>
+</h1>
+
+<p align="center">
+<a href="#installation">🐍 Installation</a> •
+<a href="#features">🚀 Features</a> •
+<a href="#example">📚 Usage example</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license">🔍 License</a>
+</p>
+
+This **Sinapsis CSM** package integrates a lightweight, efficient text-to-speech engine using the CSM model. It provides a simple template to convert input text into speech using Sinapsis.
+
+---
+
+<h2 id="installation">🐍 Installation</h2>
+
+> [!IMPORTANT]
+> Sinapsis project requires Python 3.10 or higher.
+
+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).
+
+Install with <code>uv</code>:
+```bash
+uv pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+> [!IMPORTANT]
+> Templates in each package may require additional dependencies. For development, we recommend installing the package with all the optional dependencies:
+
+With <code>uv</code>:
+```bash
+uv pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+To run this package you need a HuggingFace token. See the [official instructions](https://huggingface.co/docs/hub/security-tokens)
+and set it using
+```bash
+export HF_TOKEN=<token-provided-by-hf>
+```
+
+and test it through the cli or the webapp.
+
+Access to the following models is needed:
+
+* [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)
+* [CSM-1B](https://huggingface.co/sesame/csm-1b)
+
+---
+
+<h2 id="features">🚀 Features</h2>
+
+<h3>Templates Supported</h3>
+
+- **CSMTTS**: Converts text into speech using the CSM model.
+
+  <details>
+  <summary>Attributes</summary>
+
+  - `speaker_id` (int, default: 0): Speaker identity index.
+  - `max_audio_length_ms` (int, default: 10000): Max audio length in milliseconds.
+  - `device` ("cpu" or "cuda", default: "cpu"): Device used for inference.
+  - `context` (context: list[str] | None = None): Optional list of past utterances for context.
+  - `sample_rate_hz` (int, default: 24000): Output audio sample rate.
+  </details>
+
+---
+
+<h2 id="example">📚 Usage example</h2>
+
+This example shows how to use the **CSMTTS** template to convert text into speech and save it to disk.
+
+<details>
+<summary><strong><span style="font-size: 1.2em;">Agent config</span></strong></summary>
+
+```yaml
+agent:
+  name: csm_tts_agent
+  description: Agent that synthesizes speech from text using the CSM model.
+
+templates:
+  - template_name: InputTemplate
+    class_name: InputTemplate
+    attributes: {}
+
+  - template_name: TextInput
+    class_name: TextInput
+    template_input: InputTemplate
+    attributes:
+      text: "Hi, my name is Taylor and this is Sinapsis"
+
+  - template_name: CSMTTS
+    class_name: CSMTTS
+    template_input: TextInput
+    attributes:
+      speaker_id: 0
+      max_audio_length_ms: 10000
+      device: cpu
+      context: null
+      sample_rate_hz: 24000
+
+  - template_name: AudioWriterSoundFile
+    class_name: AudioWriterSoundFile
+    template_input: CSMTTS
+    attributes:
+      save_dir: csm_tts
+      extension: wav
+```
+
+</details>
+
+To run the config, use:
+
+```bash
+sinapsis run packages/sinapsis_csm/src/sinapsis_csm/configs/csm_agent.yml
+```
+
+> [!NOTE]
+> The `TextInput` and `AudioWriterSoundFile` templates come from the [sinapsis-data-readers](https://github.com/Sinapsis-AI/sinapsis-data-tools) and [sinapsis-data-writers](https://github.com/Sinapsis-AI/sinapsis-data-tools) packages. Make sure they are installed to use this example.
+
+---
+
+
+<h2 id="webapp">🌐 Webapp</h2>
+The webapp included in this project showcases the modularity of the CSM template for speech generation tasks.
+
+> [!IMPORTANT]
+> To run the app you first need to clone this repository:
+
+```bash
+git clone git@github.com:Sinapsis-ai/sinapsis-speech.git
+cd sinapsis-speech
+```
+
+> [!NOTE]
+> If you'd like to enable external app sharing in Gradio, `export GRADIO_SHARE_APP=True`
+
+
+<details>
+<summary id="docker"><strong><span style="font-size: 1.4em;">🐳 Docker</span></strong></summary>
+
+**IMPORTANT** This docker image depends on the sinapsis-nvidia:base image. Please refer to the official [sinapsis](https://github.com/Sinapsis-ai/sinapsis?tab=readme-ov-file#docker) instructions to Build with Docker.
+
+1. **Build the sinapsis-speech image**:
+```bash
+docker compose -f docker/compose.yaml build
+```
+
+2. **Start the app container**:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+3. **Check the logs**
+```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
+```
+
+**NOTE**: The url may be different, check the output of logs.
+
+5. **To stop the app**:
+```bash
+docker compose -f docker/compose_apps.yaml down
+```
+</details>
+
+<details>
+<summary id="virtual-environment"><strong><span style="font-size: 1.4em;">💻 UV</span></strong></summary>
+
+To run the webapp using the <code>uv</code> package manager, follow these steps:
+
+1. **Sync the virtual environment**:
+
+```bash
+uv sync --frozen
+```
+2. **Install the wheel**:
+
+```bash
+uv pip install sinapsis-speech[all] --extra-index-url https://pypi.sinapsis.tech
+```
+3. **Run the webapp**:
+
+```bash
+uv run webapps/packet_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
+```
+**NOTE**: The URL may vary; check the terminal output for the correct address.
+
+</details>
+
+
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation is available on the [Sinapsis website](https://docs.sinapsis.tech/docs).
+
+Tutorials and guides for different templates and agents are available at [docs.sinapsis.tech/tutorials](https://docs.sinapsis.tech/tutorials).
+
+---
+
+<h2 id="license">🔍 License</h2>
+
+This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the [LICENSE](LICENSE) file.
+
+For commercial use, please refer to our [official Sinapsis website](https://sinapsis.tech) for information on obtaining a commercial license.

sinapsis_csm-0.1.0/README.md

@@ -0,0 +1,230 @@
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis CSM
+<br>
+</h1>
+
+<p align="center">
+<a href="#installation">🐍 Installation</a> •
+<a href="#features">🚀 Features</a> •
+<a href="#example">📚 Usage example</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license">🔍 License</a>
+</p>
+
+This **Sinapsis CSM** package integrates a lightweight, efficient text-to-speech engine using the CSM model. It provides a simple template to convert input text into speech using Sinapsis.
+
+---
+
+<h2 id="installation">🐍 Installation</h2>
+
+> [!IMPORTANT]
+> Sinapsis project requires Python 3.10 or higher.
+
+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).
+
+Install with <code>uv</code>:
+```bash
+uv pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+> [!IMPORTANT]
+> Templates in each package may require additional dependencies. For development, we recommend installing the package with all the optional dependencies:
+
+With <code>uv</code>:
+```bash
+uv pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+To run this package you need a HuggingFace token. See the [official instructions](https://huggingface.co/docs/hub/security-tokens)
+and set it using
+```bash
+export HF_TOKEN=<token-provided-by-hf>
+```
+
+and test it through the cli or the webapp.
+
+Access to the following models is needed:
+
+* [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)
+* [CSM-1B](https://huggingface.co/sesame/csm-1b)
+
+---
+
+<h2 id="features">🚀 Features</h2>
+
+<h3>Templates Supported</h3>
+
+- **CSMTTS**: Converts text into speech using the CSM model.
+
+  <details>
+  <summary>Attributes</summary>
+
+  - `speaker_id` (int, default: 0): Speaker identity index.
+  - `max_audio_length_ms` (int, default: 10000): Max audio length in milliseconds.
+  - `device` ("cpu" or "cuda", default: "cpu"): Device used for inference.
+  - `context` (context: list[str] | None = None): Optional list of past utterances for context.
+  - `sample_rate_hz` (int, default: 24000): Output audio sample rate.
+  </details>
+
+---
+
+<h2 id="example">📚 Usage example</h2>
+
+This example shows how to use the **CSMTTS** template to convert text into speech and save it to disk.
+
+<details>
+<summary><strong><span style="font-size: 1.2em;">Agent config</span></strong></summary>
+
+```yaml
+agent:
+  name: csm_tts_agent
+  description: Agent that synthesizes speech from text using the CSM model.
+
+templates:
+  - template_name: InputTemplate
+    class_name: InputTemplate
+    attributes: {}
+
+  - template_name: TextInput
+    class_name: TextInput
+    template_input: InputTemplate
+    attributes:
+      text: "Hi, my name is Taylor and this is Sinapsis"
+
+  - template_name: CSMTTS
+    class_name: CSMTTS
+    template_input: TextInput
+    attributes:
+      speaker_id: 0
+      max_audio_length_ms: 10000
+      device: cpu
+      context: null
+      sample_rate_hz: 24000
+
+  - template_name: AudioWriterSoundFile
+    class_name: AudioWriterSoundFile
+    template_input: CSMTTS
+    attributes:
+      save_dir: csm_tts
+      extension: wav
+```
+
+</details>
+
+To run the config, use:
+
+```bash
+sinapsis run packages/sinapsis_csm/src/sinapsis_csm/configs/csm_agent.yml
+```
+
+> [!NOTE]
+> The `TextInput` and `AudioWriterSoundFile` templates come from the [sinapsis-data-readers](https://github.com/Sinapsis-AI/sinapsis-data-tools) and [sinapsis-data-writers](https://github.com/Sinapsis-AI/sinapsis-data-tools) packages. Make sure they are installed to use this example.
+
+---
+
+
+<h2 id="webapp">🌐 Webapp</h2>
+The webapp included in this project showcases the modularity of the CSM template for speech generation tasks.
+
+> [!IMPORTANT]
+> To run the app you first need to clone this repository:
+
+```bash
+git clone git@github.com:Sinapsis-ai/sinapsis-speech.git
+cd sinapsis-speech
+```
+
+> [!NOTE]
+> If you'd like to enable external app sharing in Gradio, `export GRADIO_SHARE_APP=True`
+
+
+<details>
+<summary id="docker"><strong><span style="font-size: 1.4em;">🐳 Docker</span></strong></summary>
+
+**IMPORTANT** This docker image depends on the sinapsis-nvidia:base image. Please refer to the official [sinapsis](https://github.com/Sinapsis-ai/sinapsis?tab=readme-ov-file#docker) instructions to Build with Docker.
+
+1. **Build the sinapsis-speech image**:
+```bash
+docker compose -f docker/compose.yaml build
+```
+
+2. **Start the app container**:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+3. **Check the logs**
+```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
+```
+
+**NOTE**: The url may be different, check the output of logs.
+
+5. **To stop the app**:
+```bash
+docker compose -f docker/compose_apps.yaml down
+```
+</details>
+
+<details>
+<summary id="virtual-environment"><strong><span style="font-size: 1.4em;">💻 UV</span></strong></summary>
+
+To run the webapp using the <code>uv</code> package manager, follow these steps:
+
+1. **Sync the virtual environment**:
+
+```bash
+uv sync --frozen
+```
+2. **Install the wheel**:
+
+```bash
+uv pip install sinapsis-speech[all] --extra-index-url https://pypi.sinapsis.tech
+```
+3. **Run the webapp**:
+
+```bash
+uv run webapps/packet_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
+```
+**NOTE**: The URL may vary; check the terminal output for the correct address.
+
+</details>
+
+
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation is available on the [Sinapsis website](https://docs.sinapsis.tech/docs).
+
+Tutorials and guides for different templates and agents are available at [docs.sinapsis.tech/tutorials](https://docs.sinapsis.tech/tutorials).
+
+---
+
+<h2 id="license">🔍 License</h2>
+
+This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the [LICENSE](LICENSE) file.
+
+For commercial use, please refer to our [official Sinapsis website](https://sinapsis.tech) for information on obtaining a commercial license.

sinapsis_csm-0.1.0/pyproject.toml

@@ -0,0 +1,65 @@
+[project]
+name = "sinapsis-csm"
+version = "0.1.0"
+description = "Text to speech using CSM TTS model"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [
+    {name = "SinapsisAI", email = "dev@sinapsis.tech"},
+]
+license-files = ["LICENSE"]
+dependencies = [
+    "silentcipher",
+    "csm",
+]
+
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.uv.sources]
+csm = { git = "https://github.com/Natalia-OsorioClavijo/csm.git" }
+sinapsis-csm = { workspace = true }
+silentcipher = { git = "https://github.com/SesameAILabs/silentcipher", rev = "master" }
+
+
+[tool.ruff]
+lint.select = [
+    "ARG",
+    "ANN",
+    "BLE",
+    "C4",
+    "E",
+    "F",
+    "FIX",
+    "FLY",
+    "I",
+    "PERF",
+    "PIE",
+    "RUF",
+    "RSE",
+    "SIM",
+    "SLOT",
+    "T10",
+    "T20",
+    "TD",
+    "TID",
+]
+lint.ignore = ['ANN401']
+line-length = 120
+show-fixes = true
+
+[project.urls]
+Homepage = "https://sinapsis.tech"
+Documentation = "https://docs.sinapsis.tech/docs"
+Tutorials = "https://docs.sinapsis.tech/tutorials"
+Repository = "https://github.com/Sinapsis-AI/sinapsis-speech.git"
+
+[project.optional-dependencies]
+data-tools = [
+    "sinapsis-data-readers[all]>=0.1.2",
+    "sinapsis-data-writers[soundfile]>=0.1.2",
+]
+
+all = [
+    "sinapsis-csm[data-tools]"]

sinapsis_csm-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sinapsis_csm-0.1.0/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_csm-0.1.0/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_csm-0.1.0/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_csm-0.1.0/src/sinapsis_csm.egg-info/PKG-INFO

@@ -0,0 +1,249 @@
+Metadata-Version: 2.4
+Name: sinapsis-csm
+Version: 0.1.0
+Summary: Text to speech using CSM TTS model
+Author-email: SinapsisAI <dev@sinapsis.tech>
+Project-URL: Homepage, https://sinapsis.tech
+Project-URL: Documentation, https://docs.sinapsis.tech/docs
+Project-URL: Tutorials, https://docs.sinapsis.tech/tutorials
+Project-URL: Repository, https://github.com/Sinapsis-AI/sinapsis-speech.git
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: silentcipher
+Requires-Dist: csm
+Provides-Extra: data-tools
+Requires-Dist: sinapsis-data-readers[all]>=0.1.2; extra == "data-tools"
+Requires-Dist: sinapsis-data-writers[soundfile]>=0.1.2; extra == "data-tools"
+Provides-Extra: all
+Requires-Dist: sinapsis-csm[data-tools]; extra == "all"
+
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis CSM
+<br>
+</h1>
+
+<p align="center">
+<a href="#installation">🐍 Installation</a> •
+<a href="#features">🚀 Features</a> •
+<a href="#example">📚 Usage example</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license">🔍 License</a>
+</p>
+
+This **Sinapsis CSM** package integrates a lightweight, efficient text-to-speech engine using the CSM model. It provides a simple template to convert input text into speech using Sinapsis.
+
+---
+
+<h2 id="installation">🐍 Installation</h2>
+
+> [!IMPORTANT]
+> Sinapsis project requires Python 3.10 or higher.
+
+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).
+
+Install with <code>uv</code>:
+```bash
+uv pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm --extra-index-url https://pypi.sinapsis.tech
+```
+
+> [!IMPORTANT]
+> Templates in each package may require additional dependencies. For development, we recommend installing the package with all the optional dependencies:
+
+With <code>uv</code>:
+```bash
+uv pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+Or with raw <code>pip</code>:
+```bash
+pip install sinapsis-csm[all] --extra-index-url https://pypi.sinapsis.tech
+```
+
+To run this package you need a HuggingFace token. See the [official instructions](https://huggingface.co/docs/hub/security-tokens)
+and set it using
+```bash
+export HF_TOKEN=<token-provided-by-hf>
+```
+
+and test it through the cli or the webapp.
+
+Access to the following models is needed:
+
+* [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)
+* [CSM-1B](https://huggingface.co/sesame/csm-1b)
+
+---
+
+<h2 id="features">🚀 Features</h2>
+
+<h3>Templates Supported</h3>
+
+- **CSMTTS**: Converts text into speech using the CSM model.
+
+  <details>
+  <summary>Attributes</summary>
+
+  - `speaker_id` (int, default: 0): Speaker identity index.
+  - `max_audio_length_ms` (int, default: 10000): Max audio length in milliseconds.
+  - `device` ("cpu" or "cuda", default: "cpu"): Device used for inference.
+  - `context` (context: list[str] | None = None): Optional list of past utterances for context.
+  - `sample_rate_hz` (int, default: 24000): Output audio sample rate.
+  </details>
+
+---
+
+<h2 id="example">📚 Usage example</h2>
+
+This example shows how to use the **CSMTTS** template to convert text into speech and save it to disk.
+
+<details>
+<summary><strong><span style="font-size: 1.2em;">Agent config</span></strong></summary>
+
+```yaml
+agent:
+  name: csm_tts_agent
+  description: Agent that synthesizes speech from text using the CSM model.
+
+templates:
+  - template_name: InputTemplate
+    class_name: InputTemplate
+    attributes: {}
+
+  - template_name: TextInput
+    class_name: TextInput
+    template_input: InputTemplate
+    attributes:
+      text: "Hi, my name is Taylor and this is Sinapsis"
+
+  - template_name: CSMTTS
+    class_name: CSMTTS
+    template_input: TextInput
+    attributes:
+      speaker_id: 0
+      max_audio_length_ms: 10000
+      device: cpu
+      context: null
+      sample_rate_hz: 24000
+
+  - template_name: AudioWriterSoundFile
+    class_name: AudioWriterSoundFile
+    template_input: CSMTTS
+    attributes:
+      save_dir: csm_tts
+      extension: wav
+```
+
+</details>
+
+To run the config, use:
+
+```bash
+sinapsis run packages/sinapsis_csm/src/sinapsis_csm/configs/csm_agent.yml
+```
+
+> [!NOTE]
+> The `TextInput` and `AudioWriterSoundFile` templates come from the [sinapsis-data-readers](https://github.com/Sinapsis-AI/sinapsis-data-tools) and [sinapsis-data-writers](https://github.com/Sinapsis-AI/sinapsis-data-tools) packages. Make sure they are installed to use this example.
+
+---
+
+
+<h2 id="webapp">🌐 Webapp</h2>
+The webapp included in this project showcases the modularity of the CSM template for speech generation tasks.
+
+> [!IMPORTANT]
+> To run the app you first need to clone this repository:
+
+```bash
+git clone git@github.com:Sinapsis-ai/sinapsis-speech.git
+cd sinapsis-speech
+```
+
+> [!NOTE]
+> If you'd like to enable external app sharing in Gradio, `export GRADIO_SHARE_APP=True`
+
+
+<details>
+<summary id="docker"><strong><span style="font-size: 1.4em;">🐳 Docker</span></strong></summary>
+
+**IMPORTANT** This docker image depends on the sinapsis-nvidia:base image. Please refer to the official [sinapsis](https://github.com/Sinapsis-ai/sinapsis?tab=readme-ov-file#docker) instructions to Build with Docker.
+
+1. **Build the sinapsis-speech image**:
+```bash
+docker compose -f docker/compose.yaml build
+```
+
+2. **Start the app container**:
+```bash
+docker compose -f docker/compose_apps.yaml up -d sinapsis-csm
+```
+3. **Check the logs**
+```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
+```
+
+**NOTE**: The url may be different, check the output of logs.
+
+5. **To stop the app**:
+```bash
+docker compose -f docker/compose_apps.yaml down
+```
+</details>
+
+<details>
+<summary id="virtual-environment"><strong><span style="font-size: 1.4em;">💻 UV</span></strong></summary>
+
+To run the webapp using the <code>uv</code> package manager, follow these steps:
+
+1. **Sync the virtual environment**:
+
+```bash
+uv sync --frozen
+```
+2. **Install the wheel**:
+
+```bash
+uv pip install sinapsis-speech[all] --extra-index-url https://pypi.sinapsis.tech
+```
+3. **Run the webapp**:
+
+```bash
+uv run webapps/packet_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
+```
+**NOTE**: The URL may vary; check the terminal output for the correct address.
+
+</details>
+
+
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation is available on the [Sinapsis website](https://docs.sinapsis.tech/docs).
+
+Tutorials and guides for different templates and agents are available at [docs.sinapsis.tech/tutorials](https://docs.sinapsis.tech/tutorials).
+
+---
+
+<h2 id="license">🔍 License</h2>
+
+This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the [LICENSE](LICENSE) file.
+
+For commercial use, please refer to our [official Sinapsis website](https://sinapsis.tech) for information on obtaining a commercial license.

sinapsis_csm-0.1.0/src/sinapsis_csm.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.md
+pyproject.toml
+src/sinapsis_csm/__init__.py
+src/sinapsis_csm.egg-info/PKG-INFO
+src/sinapsis_csm.egg-info/SOURCES.txt
+src/sinapsis_csm.egg-info/dependency_links.txt
+src/sinapsis_csm.egg-info/requires.txt
+src/sinapsis_csm.egg-info/top_level.txt
+src/sinapsis_csm/helpers/generator.py
+src/sinapsis_csm/templates/__init__.py
+src/sinapsis_csm/templates/csm_tts.py

sinapsis_csm-0.1.0/src/sinapsis_csm.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

sinapsis_csm-0.1.0/src/sinapsis_csm.egg-info/requires.txt

@@ -0,0 +1,9 @@
+silentcipher
+csm
+
+[all]
+sinapsis-csm[data-tools]
+
+[data-tools]
+sinapsis-data-readers[all]>=0.1.2
+sinapsis-data-writers[soundfile]>=0.1.2

sinapsis_csm-0.1.0/src/sinapsis_csm.egg-info/top_level.txt

@@ -0,0 +1 @@
+sinapsis_csm