---
license: openrail
language:
  - en
  - ko
  - es
  - pt
  - fr
pipeline_tag: text-to-speech
tags:
  - coreml
  - ios
  - macos
  - tts
  - supertonic
  - mlprogram
library_name: coremltools
---

# Supertonic-3 CoreML

CoreML ML Program exports of **Supertonic 3** for macOS and iOS.

## Variants

| Directory | Quantization | Total size |
|---|---|---|
| `models/coreml/` | fp32 (all 4 graphs) | ~197 MB |
| `models/coreml_int8_both/` | fp32 `duration_predictor`+`text_encoder`, int8 `vector_estimator`+`vocoder` | ~111 MB |

## Layout

```
models/
  coreml/                       # fp32 reference
    duration_predictor_mlprogram.mlpackage
    text_encoder_mlprogram.mlpackage
    vector_estimator_mlprogram.mlpackage
    vocoder_mlprogram.mlpackage
  coreml_int8_both/             # production-recommended variant
    ...
resources/
  voice_styles/                 # 10 voice JSONs (M1-M5, F1-F5)
  onnx/
    tts.json
    unicode_indexer.json
LICENSE
README.md
UPSTREAM.md
```

## Pipeline

The four graphs are wired the same as the upstream Supertonic-3 ONNX:
`text_processor → duration_predictor → text_encoder → vector_estimator (denoising loop) → vocoder`.

Use `resources/voice_styles/<voice>.json` to load `style_dp` (8x16) and `style_ttl` (50x256).

`resources/onnx/tts.json` carries the model config (sample rate, base chunk size,
chunk compress factor, latent dim) needed at runtime.

`resources/onnx/unicode_indexer.json` holds the multilingual tokenization tables for the v3 Unicode processor.

## Quantization details

- Method: `coremltools.optimize.coreml.linear_quantize_weights`
- Mode: `linear_symmetric`
- Bits: 8
- Granularity: `per_channel`
- Weight threshold: 2048
- Applied to: `vector_estimator`, `vocoder`
- Skipped: weights containing inf/-inf are passed through unquantized (small subset)

Sizes after quantization:
- `vector_estimator`: 127.3 MB → 65.3 MB
- `vocoder`: 48.3 MB → 24.3 MB

## Acknowledgments

- Original ONNX models, voice styles, and config: [Supertone/supertonic-3](https://huggingface.co/Supertone/supertonic-3)
- CoreML conversion pipeline: adapted from [Nooder/supertonic-2-coreml](https://github.com/Nooder/supertonic-2-coreml)

See `UPSTREAM.md` for full provenance.