Simpler-Kokoro 1.2.0

A package to make kokoro simpler to work with

SimplerKokoro

Effortless speech synthesis with Kokoro, in Python.

View on PyPI

📚 Table of Contents

• Features
• Installation
• Build from Source
• Requirements
• Examples
• Usage
• Example Output Files
• API
• License

✨ Features

• Simple interface for generating speech audio and subtitles
• Supports all Kokoro voices
• Outputs valid SRT subtitles
• Automatic Model Management

---

🚀 Installation

From PyPI:

pip install Simpler-Kokoro

Or clone the repo and install locally:

git clone https://github.com/WilleIshere/SimplerKokoro.git
cd SimplerKokoro
pip install .

---

🏗️ Build from Source

To build the package from source:

git clone https://github.com/WilleIshere/SimplerKokoro.git
cd SimplerKokoro
pip install build
python -m build

This will create distribution files in the dist/ directory:

• .whl (wheel) file for pip installation
• .tar.gz source archive

To install the built wheel locally:

pip install dist/Simpler_Kokoro-*.whl

You can now use the package as described in the usage section.

---

📦 Requirements

• Python 3.10+
• torch
• kokoro
• soundfile

_{All dependencies except Python are installed automatically.}

🧑‍💻 Examples

You can find runnable example scripts in the examples/ folder:

• basic_example.py: Basic usage, generate speech from text.
• subtitles_example.py: Generate speech with SRT subtitles.
• custom_speed_example.py: Generate speech with custom speed.
• custom_models_dir_example.py: Specify a custom directory for model downloads.

---

🛠️ Usage

Basic Example

from Simpler_Kokoro import SimplerKokoro

# Create an instance
sk = SimplerKokoro()

# List available voices
voices = sk.list_voices()
print("Available voices:", [v['name'] for v in voices])

# Generate speech
sk.generate(
    text="Hello, this is a test of the Simpler Kokoro voice synthesis.",
    voice=voices[0]['name'],
    output_path="output.wav"
)

Generate Speech with Subtitles

sk.generate(
    text="Hello, this is a test. This is another sentence.",
    voice=voices[0]['name'],
    output_path="output.wav",
    write_subtitles=True,
    subtitles_path="output.srt",
    subtititles_word_level=True
)

Generate Speech with Custom Speed

sk.generate(
    text="This is spoken faster than normal.",
    voice=voices[1]['name'],
    output_path="fast_output.wav",
    speed=1.5
)

Specify a Path to Download Models

sk.generate(
    models_dir="Folder-to-put-models-in",
    text="Thats a cool model directory.",
    voice=voices[1]['name'],
    output_path="fast_output.wav",
)

---

🖥️ Command Line Interface (CLI)

You can use the library in the command line too.

Example:

python -m Simpler_Kokoro <command> [options]

Commands and Options

Command	Description	Options
list-voices	List available Kokoro voices	--repo, --models_dir, --log_level
generate	Generate speech audio from text	--text (required), --voice (required), --output (required), --speed, --write_subtitles, --subtitles_path, --subtitles_word_level, --repo, --models_dir, --log_level

Global options:

Option	Description	Default
--repo	HuggingFace repo to use for models	hexgrad/Kokoro-82M
--models_dir	Directory to store model files	models
--log_level	Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)	INFO

Generate command options:

Option	Description	Default
--text	Text to synthesize (required)
--voice	Voice name to use (required)
--output	Output WAV file path (required)
--speed	Speech speed multiplier	1.0
--write_subtitles	Write SRT subtitles	False
--subtitles_path	Path to save subtitles	subtitles.srt
--subtitles_word_level	Word-level subtitles	False

---

📂 Example Output Files

• output.wav: The synthesized speech audio file.
• output.srt: Subtitles in SRT format (if write_subtitles=True).

Sample SRT output

1
00:00:00,000 --> 00:00:01,200
Hello,

2
00:00:01,200 --> 00:00:02,500
this is a test.

3
00:00:02,500 --> 00:00:04,000
This is another sentence.

---

📖 API

SimplerKokoro

Methods

• list_voices(): Returns a list of available voices with metadata.
• generate(text, voice, output_path, speed=1.0, write_subtitles=False, subtitles_path='subtitles.srt', subtititles_word_level=False): Generates speech audio and optional subtitles.

---

📄 License

This project is licensed under the GPL-3.0 license.

---

⭐ Star History