---
license: apache-2.0
pipeline_tag: text-to-speech
tags:
- zipvoice
- tts
- speech-synthesis
- robotics
- IB-Robot
- ascend
- onnx
- edge-deployment
---

# Model Card for ZipVoice-Distill (IB-Robot)

ZipVoice-Distill text-to-speech (flow-matching decoder + Vocos vocoder)
packaged for the [IB-Robot](https://atomgit.com/openeuler/IB_Robot) framework
with two deployments sharing one contract.

## Deployments

| deployment | backend | artifacts | notes |
|---|---|---|---|
| `ascend_310p` | Ascend ACL (Ascend310P1) | text_encoder + flow_decoder OM | fixed buckets (t256 / f1537), CFG-distilled 4-step |
| `ascend_310b` | Ascend ACL (Ascend310B1) | text_encoder + flow_decoder OM (`*_310b_origin.om`) | 310B board-side synthesis |
| `ubuntu_onnx` | ONNX Runtime CPU (torch profile) | dynamic-shape ONNX pair | host-side synthesis, 8-step default |

Shared contract: `tensor_model/zipvoice/synthesize`
(`tts.text/prompt_audio/prompt_sample_rate/prompt_text -> tts.audio`),
preprocessing `emilia-zh-cn2an-jieba-pypinyin-fixed-golden-prompt-v1`, output
`mono-float32-pcm-24000hz-vocos-cpu`.

## Provenance note

- ONNX weights re-exported from the official k2-fsa/ZipVoice ModelScope
  release (`zipvoice_distill`), sha256 pinned in the manifest artifacts.
- The 310P OM pair was converted from the same model with fixed shapes
  (`text_capacity=256`, `flow_frames=1537`, original logical revision
  `zipvoice-distill-310p1-bucket-2026-08-03`).
- Shared assets (`tokens.txt`, `vocos/pytorch_model.bin`,
  `prompts/default.npz`) are byte-identical across both deployments.
- Inference hyperparameters differ by design: 310P uses 4 diffusion steps,
  the host ONNX path defaults to 8 (see `assets/zipvoice_310p.json` vs
  `assets/zipvoice_onnx.json`).

## Repository Structure

- `inference_manifest.json` — deployment routing (schema v3, iterative request contract)
- `assets/zipvoice_310p.json` / `assets/zipvoice_onnx.json` — per-deployment runtime config
- `assets/tokens.txt`, `assets/vocos/`, `assets/prompts/` — shared assets
- `artifacts/ascend/ascend_310p/*.om` — compiled fixed-shape modules (310P)
- `artifacts/ascend_310b/*.om` — compiled fixed-shape modules (310B)
- `artifacts/onnx/*.onnx` — dynamic-shape ONNX exports

## Usage

Host: `voice_tts_service` with `bundle_path: models/zipvoice`,
`deployment: ubuntu_onnx`. Board: select `ascend_310p` through the unified
inference runtime.

## License

Code and packaging: Apache-2.0. ZipVoice model weights follow the k2-fsa/ZipVoice
upstream license.