Downloads · 30 days
36
15% of all-time downloads
KittenTTS-Mini-v0.8-ONNX
onnx-community/KittenTTS-Mini-v0.8-ONNX
KittenTTS-Mini-v0.8-ONNX is a text-to-speech model from onnx-community. Use it when you need text read aloud. It is set up for transformers.js. The card lists the license as apache-2.0.
ONNX export of KittenML/kitten-tts-mini-0.8 for browser inference with Transformers.js and ONNX Runtime Web.
All-time downloads
238
Public
Repo size
81.5 MB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.onnx78.3 MB · 96%
At a glance
- Task
- Text-to-Speech
- Library
- transformers.js
- License
- apache-2.0
- Model type
- style_text_to_speech_2
- Access
- Public
- Created
- Mar 20, 2026
- Updated
- Mar 20, 2026
- SHA
- c473d28f
Base models
Model card
From the Hugging Face model README
KittenTTS-Mini-v0.8-ONNX
ONNX export of KittenML/kitten-tts-mini-0.8 for browser inference with Transformers.js and ONNX Runtime Web.
Model Details
| Architecture | StyleTTS 2 |
| Parameters | 80M |
| Precision | Int8 quantized |
| Sample Rate | 24kHz |
| Runtime | WASM only (int8 quantized ops not supported on WebGPU) |
| Voices | Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo |
Note: This model uses int8 quantized operations (
MatMulInteger,ConvInteger,DynamicQuantizeLSTM) that are not supported by the WebGPU execution provider in ONNX Runtime Web. A FP32 version is needed for WebGPU acceleration. For WebGPU support, use KittenTTS-Nano-v0.8-ONNX (15M FP32).
Demo
KittenTTS WebGPU Demo — runs entirely in your browser.
Credits
- Models by KittenML
- Original demo: KittenTTS-Demo
- Transformers.js by HuggingFace
- phonemizer.js by Xenova
- Task
- Text-to-Speech
- Library
- transformers.js
- Type
- style_text_to_speech_2
- License
- apache-2.0
- Created
- Mar 20, 2026
- Updated
- Mar 20, 2026