Update README.md
Browse files
README.md
CHANGED
|
@@ -1,57 +1,137 @@
|
|
| 1 |
-
# Onyx-TTS
|
| 2 |
|
| 3 |
-
Onyx-TTS is a high-performance, multilingual text-to-speech system developed by 0N Labs. It's built on ONNX Runtime, delivering fast and efficient speech synthesis with minimal resource requirements.
|
| 4 |
|
| 5 |
-
<
|
| 6 |
-
<audio controls><source src="https://0N-Labs.github.io/example-
|
|
|
|
|
|
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
-
|
| 11 |
-
- **Model type**: Text-to-Speech
|
| 12 |
-
- **Languages**: Multiple languages supported
|
| 13 |
-
- **License**: Apache 2.0
|
| 14 |
-
- **Model size**: ~300MB (quantized: ~80MB)
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
|
| 19 |
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
```python
|
| 27 |
import soundfile as sf
|
| 28 |
from onyx_tts import OnyxTTS
|
| 29 |
|
| 30 |
-
# Initialize the TTS engine
|
| 31 |
onyx = OnyxTTS("onyx-v1.0.onnx", "voices-v1.0.bin")
|
| 32 |
|
| 33 |
# Generate speech
|
| 34 |
samples, sample_rate = onyx.create(
|
| 35 |
-
"Hello! This is Onyx TTS by 0N Labs.",
|
| 36 |
-
voice="af_sarah",
|
| 37 |
-
speed=1.0,
|
| 38 |
lang="en-us"
|
| 39 |
)
|
| 40 |
|
| 41 |
-
# Save
|
| 42 |
sf.write("output.wav", samples, sample_rate)
|
|
|
|
| 43 |
```
|
| 44 |
|
| 45 |
-
|
|
|
|
|
|
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
-
|
|
|
|
|
|
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
| 53 |
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
```bibtex
|
| 57 |
@software{onyx-tts,
|
|
@@ -64,6 +144,3 @@ See the latest voices and languages in the [VOICES.md](VOICES.md) file.
|
|
| 64 |
}
|
| 65 |
```
|
| 66 |
|
| 67 |
-
## Contact
|
| 68 |
-
|
| 69 |
-
For questions and support, please contact: contact@0nlabs.ai
|
|
|
|
| 1 |
+
# **Onyx-TTS**
|
| 2 |
|
| 3 |
+
Onyx-TTS is a high-performance, multilingual text-to-speech system developed by 0N Labs. It's built on **ONNX Runtime**, delivering fast and efficient speech synthesis with minimal resource requirements.
|
| 4 |
|
| 5 |
+
<p float="left">
|
| 6 |
+
<audio controls><source src="https://0N-Labs.github.io/example-one.wav" type="audio/wav"></audio>
|
| 7 |
+
<audio controls><source src="https://0N-Labs.github.io/example-two.wav" type="audio/wav"></audio>
|
| 8 |
+
</p>
|
| 9 |
|
| 10 |
+
---
|
| 11 |
|
| 12 |
+
## **Model Details**
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
* **Developed by**: 0N Labs
|
| 15 |
+
* **Model type**: Text-to-Speech
|
| 16 |
+
* **Languages**: Multiple languages supported
|
| 17 |
+
* **License**: Apache 2.0
|
| 18 |
+
* **Model size**: \~300MB (quantized: \~80MB)
|
| 19 |
|
| 20 |
+
---
|
| 21 |
|
| 22 |
+
## **Getting Started**
|
| 23 |
+
|
| 24 |
+
### **Prerequisites**
|
| 25 |
+
|
| 26 |
+
* Python 3.8 or higher
|
| 27 |
+
* `pip` (Python package manager)
|
| 28 |
+
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
### **Installation**
|
| 32 |
+
|
| 33 |
+
1. Clone the repository:
|
| 34 |
+
|
| 35 |
+
```bash
|
| 36 |
+
git clone https://github.com/0N-Labs/onyx-tts.git
|
| 37 |
+
cd onyx-tts
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
2. Create and activate a virtual environment (recommended):
|
| 41 |
+
|
| 42 |
+
```bash
|
| 43 |
+
python -m venv venv
|
| 44 |
+
source venv/bin/activate # On Windows: venv\Scripts\activate
|
| 45 |
+
```
|
| 46 |
|
| 47 |
+
3. Install the required dependencies:
|
| 48 |
+
|
| 49 |
+
```bash
|
| 50 |
+
pip install -r requirements.txt
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
### **Downloading the Model**
|
| 56 |
+
|
| 57 |
+
Download the model files from the [Releases](https://github.com/0N-Labs/onyx-tts/releases) page and place them in your project directory:
|
| 58 |
+
|
| 59 |
+
* `onyx-v1.0.onnx` (main model)
|
| 60 |
+
* `voices-v1.0.bin` (voice data)
|
| 61 |
+
|
| 62 |
+
---
|
| 63 |
+
|
| 64 |
+
### **Basic Usage**
|
| 65 |
|
| 66 |
```python
|
| 67 |
import soundfile as sf
|
| 68 |
from onyx_tts import OnyxTTS
|
| 69 |
|
| 70 |
+
# Initialize the TTS engine with the downloaded model files
|
| 71 |
onyx = OnyxTTS("onyx-v1.0.onnx", "voices-v1.0.bin")
|
| 72 |
|
| 73 |
# Generate speech
|
| 74 |
samples, sample_rate = onyx.create(
|
| 75 |
+
"Hello! This is Onyx TTS by 0N Labs.",
|
| 76 |
+
voice="af_sarah", # See available voices in VOICES.md
|
| 77 |
+
speed=1.0, # Adjust speed (0.5–2.0)
|
| 78 |
lang="en-us"
|
| 79 |
)
|
| 80 |
|
| 81 |
+
# Save the generated audio
|
| 82 |
sf.write("output.wav", samples, sample_rate)
|
| 83 |
+
print("Speech generated successfully!")
|
| 84 |
```
|
| 85 |
|
| 86 |
+
---
|
| 87 |
+
|
| 88 |
+
### **Running the Web Interface**
|
| 89 |
|
| 90 |
+
To launch the demo UI:
|
| 91 |
|
| 92 |
+
```bash
|
| 93 |
+
python web_interface.py
|
| 94 |
+
```
|
| 95 |
|
| 96 |
+
Then visit:
|
| 97 |
+
👉 [http://localhost:7860](http://localhost:7860)
|
| 98 |
|
| 99 |
+
---
|
| 100 |
+
|
| 101 |
+
## **Available Voices**
|
| 102 |
+
|
| 103 |
+
To list all available voices:
|
| 104 |
+
|
| 105 |
+
```python
|
| 106 |
+
from onyx_tts import OnyxTTS
|
| 107 |
+
|
| 108 |
+
onyx = OnyxTTS("onyx-v1.0.onnx", "voices-v1.0.bin")
|
| 109 |
+
print("Available voices:", onyx.get_voices())
|
| 110 |
+
```
|
| 111 |
+
|
| 112 |
+
See the full list in `VOICES.md`.
|
| 113 |
+
|
| 114 |
+
---
|
| 115 |
+
|
| 116 |
+
## **Troubleshooting**
|
| 117 |
+
|
| 118 |
+
If you run into issues:
|
| 119 |
+
|
| 120 |
+
1. Ensure all model files are in the correct location
|
| 121 |
+
2. Check that all dependencies are installed
|
| 122 |
+
3. Verify Python version is 3.8 or higher
|
| 123 |
+
4. Visit the [issues page](https://github.com/0N-Labs/onyx-tts/issues) for known bugs and fixes
|
| 124 |
+
|
| 125 |
+
---
|
| 126 |
+
|
| 127 |
+
## **License**
|
| 128 |
+
|
| 129 |
+
* Onyx-TTS: MIT
|
| 130 |
+
* Onyx model: Apache 2.0
|
| 131 |
+
|
| 132 |
+
---
|
| 133 |
+
|
| 134 |
+
## **Citation**
|
| 135 |
|
| 136 |
```bibtex
|
| 137 |
@software{onyx-tts,
|
|
|
|
| 144 |
}
|
| 145 |
```
|
| 146 |
|
|
|
|
|
|
|
|
|