You can deploy this model and start earning money today!

mlx-community/
MOSS-TTSD-v1.0-MLX-8bit

Name: MOSS-TTSD-v1.0-MLX-8bit
Availability: InStock

Views

No views yet

MOSS TTSD v1.0 — MLX 8-bit

This repository contains an MLX-native int8 conversion of MOSS TTSD v1.0 for multi-speaker dialogue generation on Apple Silicon.

Note This repo is a community mirror of the canonical MLX conversion maintained by AppAutomaton at appautomaton/openmoss-ttsd-mlx.

Path	Precision
`mlx-int8/`	int8 quantized weights

Command-line generation with mlx-speech:

bash

python scripts/generate_moss_ttsd.py \
  --text "[S1] Watson, I think we should go. [S2] Give me one moment." \
  --output outputs/dialogue.wav

Minimal Python usage:

python

from mlx_speech.generation import MossTTSDelayModel

model = MossTTSDelayModel.from_path("mlx-int8")

Speaker turns are tagged with [S1] and [S2] in the input text.

This repo contains the quantized MLX runtime artifact only.
The conversion keeps the original TTSD architecture and remaps weights explicitly for MLX inference.
The current runtime path is designed around speaker-tagged dialogue input and shared codec decoding.
This mirror is a duplicated repo, not an automatically synchronized namespace mirror.

Apache 2.0 — following the upstream license published with OpenMOSS-Team/MOSS-TTSD-v1.0.