---
title: Step-Audio-EditX-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Step-Audio-EditX-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Step-Audio-EditX-bf16.md"
repository: mlx-community/Step-Audio-EditX-bf16
last_updated: 2026-10-07
license: apache-2.0
model_type:
  - step1
architectures:
  - Step1ForCausalLM
base_model:
  - stepfun-ai/Step-Audio-EditX
base_model_relation: finetune
parameters: 131.2M
tensor_type:
  - F32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 261
stars: 0
tags:
  - mlx
  - speech-editing
  - step-audio
  - stepfun
  - bf16
---

# Step-Audio-EditX-bf16

> Step-Audio-EditX-bf16 - mlx-community 在 ModelScope 开源的模型。Step-Audio-EditX — bf16 MLX bundle

mlx-community/Step-Audio-EditX-bf16 是 ModelScope 魔搭社区上的 131.2M 参数机器学习模型，采用 apache-2.0 许可，基于 stepfun-ai/Step-Audio-EditX 构建。

- **Repository**: mlx-community/Step-Audio-EditX-bf16
- **License**: apache-2.0
- **Parameters**: 131.2M
- **Base model**: stepfun-ai/Step-Audio-EditX
- **Tags**: mlx, speech-editing, step-audio, stepfun, bf16
- **Downloads**: 261
- **Stars**: 0
- **Last updated**: 2026-10-07

Source: https://www.modelscope.cn/models/mlx-community/Step-Audio-EditX-bf16

---

# Step-Audio-EditX — bf16 MLX bundle

[Step-Audio-EditX](https://huggingface.co/stepfun-ai/Step-Audio-EditX) (StepFun, Apache-2.0): a 3 B audio LLM that
re-delivers an existing take — emotion, speaking style, inserted paralinguistics (laughter, sighs, breaths), denoise,
silence trim — in the same voice, plus zero-shot cloning. This is the whole pipeline in one directory of MLX
safetensors, **bf16 throughout, no quantisation**, converted from the stock checkpoint:

| file | component | source weights |
|---|---|---|
| `model.safetensors` (7.06 GB) + `config.json` | step1 LM — 32 × 3072, 48 heads / 4 KV groups, sqrt-ALiBi | `stepfun-ai/Step-Audio-EditX` |
| `vq02.safetensors` + `vq02-config.json` | Paraformer-large zh-cantonese-en online encoder (the 16.7 Hz linguistic tokenizer) | FunASR `dengcunqin/…-vocab8501-online` (FunASR model licence) |
| `vq06.safetensors` + `vq06-config.json` | S3 v1 semantic tokenizer (25 Hz, 4 096 codes) | `stepfun-ai/Step-Audio-Tokenizer` |
| `step-audio-tokenizer-assets.safetensors` | the k-means linguistic codebook + CMVN | `stepfun-ai/Step-Audio-Tokenizer` |
| `flow-model.safetensors`, `flow-conditioner.safetensors` + configs | upsample conformer + DiT flow matching (24 kHz mel) | `Step-Audio-EditX/CosyVoice-300M-25Hz/flow.pt` (StepFun-trained) |
| `hift.safetensors` + `hift-config.json` | HiFT vocoder | `…/hift.pt` (StepFun-trained) |
| `campplus.safetensors` + `campplus-config.json` | CAM++ speaker embedding | `…/campplus.onnx` (Alibaba, Apache-2.0) |
| `tokenizer.json`, `tokenizer_config.json` | the sentencepiece Unigram text tokenizer | derived from `tokenizer.model` |
| `frontend-config.json` | the 24 kHz mel front end | — |

Layout and conversion: [appautomaton/mlx-speech](https://github.com/appautomaton/mlx-speech) (MIT)
`scripts/convert/step_audio_editx.py`, run with a `--no-quantize` patch so every component stays bf16; `tokenizer.json`
was added from `tokenizer.model` (`LlamaTokenizerFast`).

## Consumers

- **Swift**: [xocialize/mlx-step-audio-editx-swift](https://github.com/xocialize/mlx-step-audio-editx-swift) —
  `EditXPipeline.load(bundle: EditXBundle(root: dir))`; quantises the LM to int8 at load when asked. Every stage is
  parity-locked against StepFun's torch code (its `PORTING-SPEC.md`).
- **Python**: `mlx-speech` — `StepAudioEditXModel.from_dir(dir)` (its resampler should be a windowed sinc; the
  shipped `np.interp` perturbs the 16 kHz tokenizers — see the Swift package's notes).

## Notes

- The Paraformer front end in the upstream code dithers with an unseeded RNG at inference (only ~96 % of its own
  codes agree run to run). Both consumers above run it deterministically (dither off).
- Measured on an M5 Max with the Swift consumer: ≈ 9.4 GB resident, ≈ 1.9 GB per edit, real-time factor 0.72–0.75
  (0.49–0.58 with the LM at int8). Content, voice and quality of the edits equal the torch reference's on the
  evaluation set (mlxengine-audio E19).

## Licence

Apache-2.0 (StepFun) for the LM, flow, HiFT and the S3 tokenizer; the Paraformer encoder under the FunASR model
licence; CAM++ Apache-2.0 (Alibaba / 3D-Speaker). Converted and re-hosted by xocialize for mlx-community.