v0.1.0 — initial release

MLX-native port of Supertone's Supertonic 3 multilingual TTS. Runs the
full flow-matching + classifier-free-guidance pipeline at ~x100 realtime
on Apple Silicon, with audio cosine 1.0 vs the cached MLX path and
cosine 0.98 vs the upstream ONNX Runtime reference.

Weights are hosted at https://huggingface.co/ambassadia/supertonic-3-mlx
and auto-downloaded on first use; this repository ships the port code,
the model card, audio samples, and a zero-config setup_and_test.sh.

Install:
    pip install git+https://gitea.tavportal.com/olivier/supertonic-3-mlx.git

Quick test:
    git clone https://gitea.tavportal.com/olivier/supertonic-3-mlx.git
    cd supertonic-3-mlx && ./setup_and_test.sh

Licenses (dual): model weights = BigScience Open RAIL-M (Section 4
propagation), port code = Apache-2.0. See LICENSE, LICENSE-CODE, NOTICE.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
transcrilive
2026-05-20 09:17:05 +02:00
commit 12dbf4a821
36 changed files with 3812 additions and 0 deletions

1
voice_styles/F1.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/F2.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/F3.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/F4.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/F5.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/M1.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/M2.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/M3.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/M4.json Normal file

File diff suppressed because one or more lines are too long

1
voice_styles/M5.json Normal file

File diff suppressed because one or more lines are too long