Sinapsis Orpheus-Cpp
Run Orpheus speech synthesis using the C++-oriented inference stack.
Overview
sinapsis-orpheus-cpp — Text to speech using Orpheus TTS model.
The package turns a specialised local TTS runtime into a reusable Sinapsis component. This helps pair text generation with audio output without building a separate process orchestration layer for the speech engine.
Where it fits
Model and inference-backend installation determine hardware support and performance; check the provided examples before choosing a voice or checkpoint.
Installation
Requires Python 3.13 or later, as declared in this package’s manifest. Install the base distribution using your preferred package manager:
uv pip install sinapsis-orpheus-cpp
# or
pip install sinapsis-orpheus-cpp
Optional features and dependencies
The base installation includes the dependencies required by the package. The following extras are declared in this package’s pyproject.toml; install only those needed by your workflow. They are standard Python optional dependencies, not separate execution profiles.
| Extra | Adds / when to select it |
|---|---|
data-tools |
Media readers/writers or data utilities for a complete pipeline. Dependencies: sinapsis-data-readers[all], sinapsis-data-writers[soundfile] |
all |
Bundle declared by this package; its manifest includes data-tools. |
For example:
uv pip install "sinapsis-orpheus-cpp[data-tools]"
The manifest also defines development-only dependency groups: dev (pre-commit, ruff, ty). These support source development and testing and are not runtime extras.
🚀 Features
Templates Supported
This module includes a template for text-to-speech synthesis using the Orpheus TTS model:
OrpheusTTS: Advanced text-to-speech synthesis template powered by Orpheus TTS, delivering human-like speech with natural intonation, emotion, and rhythm that surpasses state-of-the-art closed-source models. The template supports expressive speech synthesis through emotive tags including <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, and <gasp> for enhanced vocal expressions. Additionally, it provides multi-language support when configured with the appropriate Hugging Face model path, making it versatile for global applications.
Attributes
n_gpu_layers: Number of model layers to offload to GPU (-1 = use all layers, 0 = CPU only) (default: -1)n_threads: Number of CPU threads to use for model inference (0 = auto-detect) (default: 0)n_ctx: Context window size (maximum number of tokens, 0 = use model's maximum) (default: 8192)model_id: Hugging Face model repository ID (required)model_variant: Specific GGUF file to download from the repository (default: None)cache_dir: Directory to store downloaded models and cache files (default: SINAPSIS_CACHE_DIR)verbose: Enable verbose logging for model operations (default: False)voice_id: Voice identifier for speech synthesis (required)batch_size: Batch size for model inference (default: 1)max_tokens: Maximum number of tokens to generate for speech (default: 2048)temperature: Sampling temperature for token generation (default: 0.8)top_p: Nucleus sampling probability threshold (default: 0.95)top_k: Top-k sampling parameter (default: 40)min_p: Minimum probability threshold for token selection (default: 0.05)pre_buffer_size: Duration in seconds of audio to generate before yielding the first chunk (default: 1.5)
For example, for OrpheusTTS use sinx templates example-config OrpheusTTS to produce an example config like:
agent:
name: my_sinapsis_orpheus_cpp_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: OrpheusTTS
class_name: OrpheusTTS
template_input: InputTemplate
attributes:
n_gpu_layers: -1
n_threads: 0
n_ctx: 8192
model_id: '`replace_me:<class ''str''>`'
model_variant: null
cache_dir: ~/sinapsis_cache
verbose: false
voice_id: '`replace_me:<class ''str''>`'
batch_size: 1
max_tokens: 2048
temperature: 0.8
top_p: 0.95
top_k: 40
min_p: 0.05
pre_buffer_size: 1.5
Example Agent
The following is adapted directly from the package’s shipped orpheus_tts_app.yaml configuration. Save it as my_orpheus_cpp_agent.yaml. The example may require model checkpoints, input files, additional Template packages, or provider credentials as described in its configuration.
agent:
name: my_orpheus_cpp_agent
description: "Agent that generates speech from text using the Orpheus TTS model."
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: OrpheusTTS
class_name: OrpheusTTS
template_input: InputTemplate
attributes:
n_gpu_layers: -1
n_ctx: 30000
model_id: "Mungert/orpheus-3b-0.1-ft-GGUF"
model_variant: "orpheus-3b-0.1-ft-iq3_xxs.gguf"
voice_id: "tara"
temperature: 0.8
top_p: 0.95
top_k: 40
min_p: 0.05
pre_buffer_size: 1.5
max_tokens: 4096
sinx jobs run my_orpheus_cpp_agent.yaml
More configurations: orpheus_tts_app.yaml, orpheus_tts.yaml.
Documentation
License
Sinapsis open-source components are available under your choice of the MIT License or the Apache License 2.0, unless otherwise noted.
Metadata
Release files for sinapsis-orpheus-cpp 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| sinapsis_orpheus_cpp-1.0.0.tar.gz | 147.4 kB | Without provenance | Details for sinapsis_orpheus_cpp-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sinapsis_orpheus_cpp-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for sinapsis_orpheus_cpp-1.0.0-py3-none-any.whl |
Total release size: 163.5 kB
Release files / sinapsis_orpheus_cpp-1.0.0.tar.gz
| Download URL | sinapsis_orpheus_cpp-1.0.0.tar.gz |
|---|---|
| Size | 147.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d3a0f612ea890bf2a8e536eef86758cecc33c1029b6fe3da6d63ddd032bc22a4
|
|
BLAKE2b-256 checksum How to use checksums |
2f5915cd810258586b54958ac8afaf7a485b493ec27dc9e7944181be33f08586
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.17
|
Release files / sinapsis_orpheus_cpp-1.0.0-py3-none-any.whl
| Download URL | sinapsis_orpheus_cpp-1.0.0-py3-none-any.whl |
|---|---|
| Size | 16.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cdbe346f74c87673724621b1aae9c83f5328395d7e0bd09fc8ae78f990cbdc48
|
|
BLAKE2b-256 checksum How to use checksums |
78f75c26fdd9ffd11ab2538306ac3febafec44d00c3c119b8a9d8a62e505fc22
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.17
|
Security for sinapsis-orpheus-cpp 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.