Text-to-Speech
LiteRT
LiteRT
ONNX
Core ML
PyTorch
tts
singing
singing-voice-synthesis
multilingual
expressive-tts
duration-flow
Instructions to use spybyscript/scyllasband with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use spybyscript/scyllasband 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
- Notebooks
- Google Colab
- Kaggle
Commit History
10 days ago
-
Scylla's Band v4-20261106: speech and singing from one model (a delivery mode on the flow, a BigVGAN singing decoder); LiteRT, ONNX, WebGPU, Core ML, Core AI and PyTorch
Verified signatureb0fe862
11 days ago
-
Add Core AI and Core ML bundles for v3-20261104; model card with Apple bundles and v3-20261104 performance
Verified signature6e3fd46 -
Scylla's Band v3-20261104
Verified signature16f3dd0 -
Model card: Core ML and Core AI bundles of v3-20261103 (tag v3-20261103-apple), v3 performance
Verified signature15ac508 -
Add Core AI and Core ML bundles for v3-20261103
Verified signature53c0c25 -
Scylla's Band v3-20261103
Verified signaturee51e345
16 days ago
-
LiteRT bundle exported again from the v2-20261020 weights, with faster first audio
Verified signatureSame model and release_id (v2-20261020). The litert/ bundle is re-exported with lowkeytea/datasetGen full_retrain/export_litert.py --quantize int8: INT8 weights only on fully connected, convolution and embedding layers, latent buckets every 64 frames, prefix-less first-segment flow graphs, narrower span and G2P widths. Model card: the LiteRT rows, the bundle description and its validation. Needs the runtime at lowkeytea/scyllasband b2c85d0 or later for the new graphs; earlier runtimes use its full-size graphs.c12adda
25 days ago
-
Add Core ML and Core AI bundles of v2-20261020 and performance measurements
Verified signature42d06ab -
Scylla's Band v2-20261020
Verified signatured933c90
-
Add Core ML and Core AI bundles of v2-20261006 and performance measurements
Verified signatured48a314 -
Scylla's Band v2-20261006
Verified signature86bbe7a -
Publish inference weights only and add third-party notices
Verified signature497346d -
Describe passage-based long-form synthesis in the model card
Verified signature24f9bf8
-
Soften the joyful delivery preset in the model card
Verified signature3211b3a -
Add Core ML and Core AI bundles of v2-20261005
Verified signature13be636 -
Add a delivery primer to the model card
Verified signature6b84e6d -
Scylla's Band v2-20261005
Verified signature097347e
-
Replace development v2 with measured delivery model; preserve v1 separately
Verified signature7d1858c
-
Publish v2 coherent duration hierarchy
Verified signature5fb4f60
-
Finalize v2 word-boundary duration refresh
Verified signature4ae948e
-
Publish Scyllas Band v2 card and checksums
Verified signature1cc6936