Text-to-Speech
LiteRT
LiteRT
Supertonic
supertonic_3
tts
on-device
android
qualcomm
npu
flow-matching
Instructions to use soniqo/Supertonic-3-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use soniqo/Supertonic-3-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Supertonic
How to use soniqo/Supertonic-3-LiteRT with Supertonic:
from supertonic import TTS tts = TTS(auto_download=True) style = tts.get_voice_style(voice_name="M1") text = "The train delay was announced at 4:45 PM on Wed, Apr 3, 2024 due to track maintenance." wav, duration = tts.synthesize(text, voice_style=style) tts.save_audio(wav, "output.wav")
- Notebooks
- Google Colab
- Kaggle
model card: add ecosystem + cross-format + docs links
Browse files
README.md
CHANGED
|
@@ -47,3 +47,21 @@ Assets to drive them: `tts.json`, `unicode_indexer.json` (G2P-free tokenizer), `
|
|
| 47 |
- **Weights**: derivative of [`Supertone/supertonic-3`](https://huggingface.co/Supertone/supertonic-3)
|
| 48 |
(commit `3cadd1ee6394adea1bd021217a0e650ede09a323`), Supertone Inc., [arXiv:2503.23108](https://arxiv.org/abs/2503.23108) β **OpenRAIL-M**
|
| 49 |
(use-based restrictions carry over).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
- **Weights**: derivative of [`Supertone/supertonic-3`](https://huggingface.co/Supertone/supertonic-3)
|
| 48 |
(commit `3cadd1ee6394adea1bd021217a0e650ede09a323`), Supertone Inc., [arXiv:2503.23108](https://arxiv.org/abs/2503.23108) β **OpenRAIL-M**
|
| 49 |
(use-based restrictions carry over).
|
| 50 |
+
|
| 51 |
+
## Other Supertonic-3 formats
|
| 52 |
+
|
| 53 |
+
- [**Supertonic-3 β ONNX (INT8)**](https://huggingface.co/soniqo/Supertonic-3-ONNX-INT8) β server / desktop (ONNX Runtime).
|
| 54 |
+
- [**Supertonic-3 β CoreML**](https://huggingface.co/aufklarer/Supertonic-3-CoreML) β iOS / Apple Neural Engine (.mlpackage).
|
| 55 |
+
|
| 56 |
+
## Ecosystem
|
| 57 |
+
|
| 58 |
+
- [**soniqo.audio**](https://soniqo.audio) β website / use-case explorer (transcription, voice cloning, live ASR, voice agents).
|
| 59 |
+
- [**speech-core**](https://github.com/soniqo/speech-core) β C++ orchestration library; Supertonic plugs in as a `TTSInterface` LiteRT model.
|
| 60 |
+
- [**speech-swift**](https://github.com/soniqo/speech-swift) β Apple Silicon MLX + CoreML runtime.
|
| 61 |
+
- [**speech-android**](https://github.com/soniqo/speech-android) β Android SDK consuming on-device LiteRT bundles.
|
| 62 |
+
|
| 63 |
+
## Other LiteRT models in this collection
|
| 64 |
+
|
| 65 |
+
- [VoxCPM2 β LiteRT (INT8)](https://huggingface.co/soniqo/VoxCPM2-LiteRT-INT8) (TTS)
|
| 66 |
+
- [Parakeet TDT 0.6B v3 β LiteRT (INT8)](https://huggingface.co/soniqo/Parakeet-TDT-0.6B-v3-LiteRT-INT8) Β· [Nemotron Speech Streaming β LiteRT](https://huggingface.co/soniqo/Nemotron-Speech-Streaming-LiteRT) (ASR)
|
| 67 |
+
- [Silero VAD v5 β LiteRT](https://huggingface.co/soniqo/Silero-VAD-v5-LiteRT) (VAD)
|