---
license: apache-2.0
base_model: stepfun-ai/Step-Audio-EditX
library_name: mlx
pipeline_tag: audio-to-audio
language:
- en
- zh
tags:
- mlx
- speech-editing
- step-audio
- stepfun
- quantized
- 8bit
---

# Step-Audio-EditX — int8 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
[bf16 bundle](https://huggingface.co/mlx-community/Step-Audio-EditX-bf16) with the **step1 LM quantised to 8 bits**
(affine, group 64, every Linear and the embeddings — `model.safetensors` 3.75 GB instead of 7.06 GB); the tokenizers,
flow, HiFT and CAM++ are the bf16 files unchanged. `config.json` carries
`"quantization": {"bits": 8, "group_size": 64, "mode": "affine"}`.

The quantised weights were written by the Swift consumer itself from the bf16 bundle (`editx-gates
--write-int8-bundle`, quantised on MLX's CPU stream), so loading this bundle reproduces quantise-at-load exactly.

| file | component | source |
|---|---|---|
| `model.safetensors` (3.75 GB, int8) + `config.json` | step1 LM — 32 × 3072, 48 heads / 4 KV groups, sqrt-ALiBi | `stepfun-ai/Step-Audio-EditX` |
| `vq02.safetensors`, `vq06.safetensors`, `step-audio-tokenizer-assets.safetensors` + configs | the dual tokenizer (bf16) | FunASR Paraformer (FunASR model licence) / `stepfun-ai/Step-Audio-Tokenizer` |
| `flow-model.safetensors`, `flow-conditioner.safetensors`, `hift.safetensors`, `campplus.safetensors` + configs | flow, vocoder, speaker (bf16) | StepFun-trained / Alibaba CAM++ (Apache-2.0) |
| `tokenizer.json`, `tokenizer_config.json`, `frontend-config.json` | text tokenizer, mel front end | derived from `tokenizer.model` |

## Consumers

- **Swift**: [xocialize/mlx-step-audio-editx-swift](https://github.com/xocialize/mlx-step-audio-editx-swift) ≥ 0.1.1 —
  `EditXPipeline.load(bundle:)` reads the quantisation from `config.json`.
- **Python**: `mlx-speech` loads int8 LM bundles of this layout (its `--bits 8` converter writes the same keys).

## Measured (M5 Max, the Swift consumer, the E19 evaluation cues)

- Resident 6.2 GB phys_footprint after load (MLX active 5.7 GB); MLX peak 7.3–7.7 GB per edit; real-time factor
  **0.51–0.53** (bf16: 0.72–0.75); loads in 0.5 s.
- Content survives every edit (ASR error 0.000 on the four test edits), speaker similarity 0.83–0.97 to the source,
  DNSMOS 3.45–3.49 — the same bars as bf16 and the torch reference. Sampled tokens differ from bf16's at near-ties,
  as any quantised tier's do.

## 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). Quantised and re-hosted by xocialize for mlx-community.