Text-to-Speech
Supertonic
ONNX
Korean
Japanese
English
tts
axera
ax650
ax8850
llm-8850
axcl
npu
pulsar2
Instructions to use jonpark0/supertonic-3-AX650 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use jonpark0/supertonic-3-AX650 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
Commit History
17 days ago
-
Two-bucket support is now on TTSBot main
Verified signaturea12032f -
Add a 192-frame bucket (about 13 s per call)
Verified signaturest_est_T192_L192.axmodel, st_voc_L192.axmodel and st_rope_T192_L192.onnx: the same conversion with text and latent length 192, calibrated on 7-13 s sentences. README and NOTICE describe the second bucket and its card results.36be394 -
Add Supertonic 3 estimator and vocoder for AX650/AX8850
Verified signature108ca49 -
initial commit
Verified signatureefca926