claire-speech-engine 1.0.0b1

A backend-agnostic framework for advanced speech synthesis.

The Claire Speech Engine (CSE)

The Claire Speech Engine is a production-grade, backend-agnostic speech synthesis library built in Python.

Installation

pip install claire-speech-engine

To install from source for development:

git clone https://github.com/Yukariii04/Claire-Speech-Engine.git
cd Claire-Speech-Engine
pip install -e ".[dev]"

Quick Start

The quickest way to see CSE in action is using the CLI or the Python API.

CLI

# List available voices
cse voices

# Generate speech
cse speak --voice claire --text "Hello from The Claire Speech Engine."

Python API

from cse import SpeechEngine

engine = SpeechEngine()
engine.load_voice("claire")

speech = engine.speak("Synthesis is now extremely simple.")
if speech.success:
    print(f"Audio saved to: {speech.audio_path}")

Examples

We believe every feature should be easily discoverable. Check the examples/ directory for runnable scripts:

• examples/basic.py — Simple end-to-end synthesis.
• examples/configuration.py — How to pass custom overrides and load configurations.
• examples/list_voices.py — Querying the local voice registry.
• examples/generate_speech.py — Handling output files and moving them dynamically.

Architecture & Vision

Read these documents to understand the core philosophy and design of the engine:

• Project Vision Document (PVD-001)
• Architecture Overview

Roadmap

The Claire Speech Engine (CSE) has officially reached v1.0.0-beta. The core framework is now feature-frozen to ensure a stable foundation.

Future development will transition to:

1. CPE (Claire Performance Engine): Prosody, emotion, and dialogue planning.
2. CSM (Claire Speech Model): Core acoustic ML model training.

License

This project is licensed under the MIT License. See the LICENSE file for details.

---

Development

Running Tests

pytest

Running Benchmarks

pytest benchmarks/ --benchmark-only

See docs/Benchmarks/README.md for full performance targets and reports.