---
title: MOSS-TTS-Local-Transformer-v1.5-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16.md"
repository: mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16
last_updated: 2026-09-03
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - moss_tts_local
architectures:
  - MossTTSLocalModel
base_model:
  - OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5
base_model_relation: finetune
parameters: 4.6B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - zh
  - en
  - ja
  - ko
  - de
  - fr
  - es
  - it
  - ru
  - pt
downloads: 31
stars: 0
tags:
  - mlx
  - mlx-audio
  - text-to-speech
  - voice-cloning
  - streaming
  - apple-silicon
---

# MOSS-TTS-Local-Transformer-v1.5-bf16

> MOSS-TTS-Local-Transformer-v1.5-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16

mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16 是 ModelScope 魔搭社区上的 4.6B 参数text-to-speech模型，采用 apache-2.0 许可，基于 OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5 构建。

- **Repository**: mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 4.6B
- **Base model**: OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5
- **Tags**: mlx, mlx-audio, text-to-speech, voice-cloning, streaming, apple-silicon
- **Downloads**: 31
- **Stars**: 0
- **Last updated**: 2026-09-03

Source: https://www.modelscope.cn/models/mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16

---

# mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16

MLX conversion of [OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5)
(OpenMOSS / MOSI.AI) — the 4B `MossTTSLocal` speech model (Qwen3 backbone + a local transformer
emitting 12 RVQ codebooks per frame), zero-shot voice cloning, streaming synthesis, 48 kHz stereo
output through [MOSS-Audio-Tokenizer-v2](https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer-v2).

Precision: **bf16 (unquantized, weights as upstream)** — 8.5 GB. Converted with `mlx_audio.convert`
(model type `moss_tts_local`) from the upstream safetensors, tokenizer files copied verbatim;
the upstream remote-code `.py` files are not needed by MLX and were dropped.

Sibling tiers: `MOSS-TTS-Local-Transformer-v1.5-bf16` · `-8bit` · `-4bit`. The codec is
[mlx-community/MOSS-Audio-Tokenizer-v2-bf16](https://huggingface.co/mlx-community/MOSS-Audio-Tokenizer-v2-bf16)
(this config's `audio_tokenizer_name_or_path` still points at the upstream fp32 repo, which
mlx-audio also loads directly).

## Use with mlx-audio

```python
from mlx_audio.tts import load
from mlx_audio.audio_io import write as audio_write

model = load("mlx-community/MOSS-TTS-Local-Transformer-v1.5-bf16", lazy=True)
result = next(model.generate(
    text="Hello, this is MOSS-TTS running on MLX.",
    ref_audio="speaker.wav",          # optional zero-shot cloning prompt
    language="English",
    max_tokens=400,
))
audio_write("out.wav", result.audio, result.sample_rate)   # 48 kHz stereo
```

Streaming (`stream=True, streaming_interval=2.0`) is supported on this checkpoint; see the
mlx-audio `moss_tts` README. Fixed 12-codebook RVQ depth — do not pass a different
`n_vq_for_inference`.

## License

Apache-2.0 (upstream weights and this conversion). Please credit OpenMOSS for the model.