Total runs:
280.5K
Run Growth:
994
Growth Rate:
0.35%
Sponsored by
PoYo.AI
FluidInference / supertonic-3-coreml
Model's Last Updated: June 07 2026
text-to-speech
Introduction of supertonic-3-coreml
Model Details of supertonic-3-coreml
🧃 supertonic-3: Multilingual Text-to-Speech CoreML
|
On‑device multilingual TTS model converted to Core ML for Apple platforms. This is a hand‑port of Supertone Supertonic‑3 v1.7.3 from ONNX → PyTorch → Core ML, suitable for FluidAudio's TTS pipeline on macOS/iOS. 31 languages, 44.1 kHz output, flow‑matching diffusion with classifier‑free guidance (8 denoising steps).
The conversion script is here: https://github.com/FluidInference/mobius/tree/main/models/tts/supertonic-3/coreml
And the FluidAudio integration is here: https://github.com/FluidInference/FluidAudio/tree/main/Sources/FluidAudio/TTS/Supertonic3
Highlights
- Core ML : Runs on‑device (ANE + CPU) on Apple Silicon.
- Multilingual : 31 languages — see Supported Languages .
- High quality : 44.1 kHz output via flow‑matching diffusion + ConvNeXt vocoder.
- Voice styling : zero‑shot voice style embeddings (single JSON per voice).
- Performance : end‑to‑end RTFx ≈ 8.5× on M2 (CoreML), ≈ 17–19× on M2 with current ANE assignment (3 of 4 modules on ANE).
- Privacy : No network calls required once models are downloaded.
Intended Use
- Batch TTS for full text segments on macOS/iOS.
- Local voice synthesis for note‑taking, accessibility, and creative tools.
- Embedded TTS in production apps via the FluidAudio Swift framework.
Supported Platforms
- macOS 14+ (Apple Silicon recommended)
- iOS 17+
Model Details
-
Architecture
: Supertonic‑3 v1.7.3 — 4‑stage pipeline:
-
text_encoder— token embeddings → contextual text features[B, 256, T]. -
duration_predictor— predicts utterance duration from text features. -
vector_estimator— flow‑matching diffusion in latent space (8 steps, classifier‑free guidance via batch‑2 duplication, ConvNeXt + cross‑attention to text + style attention). -
vocoder— ConvNeXt decoder → 44.1 kHz waveform.
-
- Output audio : 44.1 kHz mono, Float32 PCM.
- Languages : 31 (see below).
- Precision : FP16 weights and activations (mlprogram, iOS 18+ minimum deployment target).
- Granularity : vocoder frame ≈ 11.6 ms; latent tick ≈ 69.7 ms.
Supported Languages
English, Korean, Japanese, Arabic, Bulgarian, Czech, Danish, German, Greek, Spanish, Estonian, Finnish, French, Hindi, Croatian, Hungarian, Indonesian, Italian, Lithuanian, Latvian, Dutch, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Swedish, Turkish, Ukrainian, Vietnamese.
Performance (Apple M2, macOS 26.5, FP16)
| Module | Size | Predict | Compute placement |
|---|---|---|---|
| duration_predictor | 1.8 MB | 0.82 ms | CPU (tiny) |
| text_encoder | 17 MB | 2.15 ms | 62 % ANE |
| vocoder | 48 MB | 1.17 ms | 100 % ANE |
| vector_estimator (fp16) | 122 MB | 9.29 ms | CPU + GPU (see notes) |
| vector_estimator (int8) | 62 MB | ~same | int8 weight-only / fp16 acts; ~10 % lower peak RSS, RMSE ≈ 0.016 vs FP16 |
End‑to‑end on M2: ≈ 0.74 s to synthesize 6.32 s of audio for a single English sentence (RTFx ≈ 8.5×), 8 denoising steps. Output verified against FluidAudio Parakeet TDT ASR.
Note on
vector_estimator
: 100 % of its ops are ANE‑eligible after
the float‑mask + precompute refactor, but Apple's ANECCompile currently
returns opaque error 11 on this graph and silently falls back to CPU/GPU.
See
coreml/trials.md
in the conversion repo for the full investigation.
Files
Both
.mlpackage
(Core ML source bundle, includes weights + spec) and the
precompiled
.mlmodelc
(ready for direct
MLModel(contentsOf:)
load) are
shipped — use
.mlmodelc
to skip the on‑device compile step on first load.
-
TextEncoder.mlpackage/TextEncoder.mlmodelc— fixedT=128text input. -
DurationPredictor.mlpackage/DurationPredictor.mlmodelc— fixedT=128text input. -
VectorEstimator.mlpackage/VectorEstimator.mlmodelc—latent.Landtext.Tas RangeDim(17..512), FP16 weights (122 MB). -
VectorEstimator_int8.mlpackage/VectorEstimator_int8.mlmodelc— same model, int8 weight-only (per-channel symmetric) + FP16 activations (62 MB; ~10 % lower peak RSS, RMSE ≈ 0.016 vs FP16). -
Vocoder.mlpackage/Vocoder.mlmodelc—latent.L_ttlas RangeDim(4..512). -
tts.json— token / text frontend configuration. -
unicode_indexer.json— Unicode → token id mapping (multilingual frontend). -
voice_styles/M1.json— example voice style embedding (single male reference). -
manifest.json— file inventory (sha256 + sizes) for both.mlpackageand.mlmodelc. -
infer.py— minimal self-contained Python demo (loads.mlmodelc/.mlpackagedirectly). -
requirements.txt— Python deps forinfer.py(coremltools,numpy,soundfile).
Usage
Quick test (Python)
For the curious / for sanity checking, this repo ships a small self‑contained
script
infer.py
that loads all four modules directly via
coremltools
and
writes a 44.1 kHz WAV. No external repo clone required.
# 1. Download the repo (e.g. via huggingface_hub or `git lfs clone`).
git lfs clone https://huggingface.co/FluidInference/supertonic-3-coreml
cd supertonic-3-coreml
# 2. Install the 3 deps (macOS, Python 3.11+ recommended).
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
# 3. Synthesize.
python infer.py "Hello, world." --voice-style voice_styles/M1.json -o hello.wav
python infer.py "Bonjour le monde." --lang fr --voice-style voice_styles/M1.json -o fr.wav
# Use the int8-quantized VectorEstimator (62 MB instead of 122 MB).
python infer.py "Hello, int8 build." --vector-estimator VectorEstimator_int8.mlpackage -o int8.wav
# Optional: pick a compute unit explicitly.
python infer.py "Test" --compute-units CPU_AND_NE -o ne.wav
The Python script loads
.mlpackage
(which is what
coremltools
accepts);
the
.mlmodelc
bundles are for direct Swift / Objective‑C use
(
MLModel(contentsOf:)
) where they skip the on‑device compile step.
Production (Swift / FluidAudio)
For production use, the FluidAudio Swift framework handles model loading, text frontend, batching, chunking, and the diffusion / vocoder loop.
Swift (FluidAudio)
import AVFoundation
import FluidAudio
Task {
// Download and load Supertonic-3 models (first run only)
let models = try await Supertonic3Models.downloadAndLoad()
// Initialize the TTS manager
let tts = Supertonic3Manager(config: .default)
try await tts.initialize(models: models)
// Synthesize speech for some text with a voice style
let style = try VoiceStyle.load(path: "voice_styles/M1.json")
let audio = try await tts.synthesize(text: "Hello, world.", style: style)
// audio.samples is 44.1 kHz Float32 PCM in [-1, 1]
try AudioWriter.writeWav(audio.samples, sampleRate: 44_100, to: "hello.wav")
tts.cleanup()
}
For more examples (including CLI usage and benchmarking), see the FluidAudio repository: https://github.com/FluidInference/FluidAudio
Limitations
- 44.1 kHz output is high quality but heavier than 16/22.05 kHz TTS — plan for the bandwidth and storage cost.
-
vector_estimatorcurrently runs on CPU + GPU instead of ANE due to an Apple‑side ANE compiler limitation (see Performance ). -
Text frontend currently uses fixed
T=128token windows; longer text must be segmented by the caller.
License
OpenRAIL‑M (inherited from upstream Supertone/supertonic-3 ). The Core ML conversion tooling and FluidAudio integration are MIT‑licensed. See the FluidAudio repository for details and usage guidance.
Runs of FluidInference supertonic-3-coreml on huggingface.co
179
Total runs
0
24-hour runs
-1
3-day runs
42
7-day runs
50
30-day runs
More Information About supertonic-3-coreml huggingface.co Model
Url of supertonic-3-coreml
supertonic-3-coreml huggingface.co Url
Provider of supertonic-3-coreml huggingface.co
Other API from FluidInference
Updated:August 20 2026
Total runs:
114.4K
Run Growth:
81.1K
Growth Rate:
71.14%
Total runs:
31.7K
Run Growth:
1.0K
Growth Rate:
3.24%
Total runs:
17.0K
Run Growth:
1.4K
Growth Rate:
8.54%
Total runs:
12.0K
Run Growth:
-1.3K
Growth Rate:
-11.00%
Total runs:
10.3K
Run Growth:
1.2K
Growth Rate:
11.40%
Total runs:
2.4K
Run Growth:
117
Growth Rate:
5.00%
Total runs:
1.7K
Run Growth:
157
Growth Rate:
9.13%
Total runs:
959
Run Growth:
-314
Growth Rate:
-32.74%
Total runs:
744
Run Growth:
14
Growth Rate:
1.90%
Total runs:
534
Run Growth:
470
Growth Rate:
88.01%
Total runs:
323
Run Growth:
311
Growth Rate:
100.00%
Total runs:
281
Run Growth:
0
Growth Rate:
0.00%
Total runs:
266
Run Growth:
6
Growth Rate:
2.31%
Total runs:
264
Run Growth:
248
Growth Rate:
100.00%
Total runs:
259
Run Growth:
151
Growth Rate:
100.00%
Total runs:
232
Run Growth:
151
Growth Rate:
65.09%
Total runs:
215
Run Growth:
-13
Growth Rate:
-6.05%
Total runs:
142
Run Growth:
44
Growth Rate:
35.20%
Total runs:
132
Run Growth:
-108
Growth Rate:
-83.08%
Total runs:
113
Run Growth:
65
Growth Rate:
63.73%
Total runs:
85
Run Growth:
51
Growth Rate:
60.00%
Total runs:
66
Run Growth:
0
Growth Rate:
0.00%
Total runs:
54
Run Growth:
12
Growth Rate:
22.22%
Total runs:
53
Run Growth:
53
Growth Rate:
100.00%
Total runs:
52
Run Growth:
36
Growth Rate:
69.23%
Total runs:
43
Run Growth:
-3
Growth Rate:
-6.98%
Total runs:
43
Run Growth:
0
Growth Rate:
0.00%
Total runs:
42
Run Growth:
-13
Growth Rate:
-30.95%
Total runs:
42
Run Growth:
1
Growth Rate:
100.00%
Total runs:
41
Run Growth:
0
Growth Rate:
0.00%
Total runs:
40
Run Growth:
29
Growth Rate:
100.00%
Total runs:
38
Run Growth:
5
Growth Rate:
13.16%
Total runs:
36
Run Growth:
0
Growth Rate:
0.00%
Total runs:
36
Run Growth:
26
Growth Rate:
72.22%
Total runs:
31
Run Growth:
-2
Growth Rate:
-6.45%
Total runs:
30
Run Growth:
0
Growth Rate:
0.00%
Total runs:
29
Run Growth:
-15
Growth Rate:
-51.72%
Total runs:
27
Run Growth:
-13
Growth Rate:
-50.00%
Total runs:
20
Run Growth:
5
Growth Rate:
25.00%
Total runs:
15
Run Growth:
-5
Growth Rate:
-33.33%
Total runs:
12
Run Growth:
7
Growth Rate:
100.00%
Total runs:
10
Run Growth:
-8
Growth Rate:
-80.00%
Total runs:
10
Run Growth:
1
Growth Rate:
10.00%
Total runs:
6
Run Growth:
4
Growth Rate:
66.67%
Total runs:
6
Run Growth:
5
Growth Rate:
83.33%
Total runs:
4
Run Growth:
-1
Growth Rate:
-25.00%
Total runs:
4
Run Growth:
3
Growth Rate:
100.00%
Total runs:
4
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
-3
Growth Rate:
-75.00%
Total runs:
3
Run Growth:
-5
Growth Rate:
-166.67%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
1
Run Growth:
-1
Growth Rate:
-100.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%