Text-to-Speech
ONNX
Supertonic
Vietnamese
English
tts
vietnamese
code-switching
onnxruntime
on-device
flow-matching
Instructions to use dogenthq/KorvaTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use dogenthq/KorvaTTS 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
-
Describe training data without hour count
Verified signaturee5c8c21 -
Add heykorva.com online demo link
Verified signatureafbc31d
-
Fix remaining tail burst in samples (improved burst detection)
Verified signature157f4ad -
Regenerate all samples with tail cleanup (no clicks)
Verified signature8a981ce -
Fix end-of-audio artifacts in samples (trim trailing burst, add fade-out)
Verified signaturee8e6f5c -
Update ngoc_huyen sample
Verified signature4aa1c25 -
Update gia_bao, huu_dat, phuong_linh, thanh_phong samples
Verified signature819a119 -
Regenerate all voice samples at speed 1.05
Verified signatureb22b0bd -
Update phuong_linh sample sentence
Verified signaturedf5034e -
Regenerate phuong_linh sample with new sentence
Verified signaturea452bdd -
Regenerate ngoc_huyen sample
Verified signatureb153fb6 -
Voices table: Ref left, Sample right
Verified signature2ded65a -
Reorder model card sections
Verified signatureaae0d82 -
Add synthesized voice samples
Verified signature0ebc827 -
Add synthesized voice samples (model card)
Verified signatureb3b00c3 -
Add Discord community link
Verified signature9de3b5b -
Upload KorvaTTS assets
Verified signature7e8fa6a -
Upload KorvaTTS assets (model card)
Verified signature5afdffd -
initial commit
Verified signature9ac0391