---
license: apache-2.0
base_model: lakucho/MOSS-Audio-8B-Instruct
tags:
- comfyui
- safetensors
- repackaged
pipeline_tag: audio-text-to-text
language:
- en
- zh
---

# MOSS-Audio-8B-Instruct-ComfyUI

Instruction-following audio understanding and transcription with text output.

This is a converted model package for [Jack Spooner’s ComfyUI fork](https://github.com/jackspooner/ComfyUI), derived from [lakucho/MOSS-Audio-8B-Instruct](https://huggingface.co/lakucho/MOSS-Audio-8B-Instruct/tree/8bd5b22c64dd80b59c06af4e3304e581a3e5596b). It is not a new fine-tune.

## Required code

The integration modifies ComfyUI core; this is not a drop-in `custom_nodes` package.

- [Model integration commit](https://github.com/jackspooner/ComfyUI/commit/624b1ae48b67ba7fc0fae074e77f6091fbb68633)
- [Implementation](https://github.com/jackspooner/ComfyUI/blob/9d9053c5e7a272f1769886f4d89b6f8a7c79c785/comfy/text_encoders/moss_audio.py) · [Offline converter](https://github.com/jackspooner/ComfyUI/blob/9d9053c5e7a272f1769886f4d89b6f8a7c79c785/scripts/convert_moss_audio.py)
- [Development branch](https://github.com/jackspooner/ComfyUI/tree/moss-audio-native) · [Pinned compatible reference snapshot `9d9053c5e`](https://github.com/jackspooner/ComfyUI/tree/9d9053c5e7a272f1769886f4d89b6f8a7c79c785)
- [Installation, node usage and acceptance details](https://github.com/jackspooner/ComfyUI/blob/9d9053c5e7a272f1769886f4d89b6f8a7c79c785/docs/moss-audio.md)

For an existing ComfyUI installation, use the linked core changes and their prerequisites against a compatible base. The integration commit alone is not asserted to be an independently cherry-pickable patch. The pinned reference snapshot includes the required shared loaders, attention and memory changes. Follow the fork’s installation README and dependencies when reproducing that snapshot; update the application only while its queue is idle. Upstream ComfyUI is [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI); its [README](https://github.com/Comfy-Org/ComfyUI/blob/master/README.md) describes the underlying node engine and model management.

## Files and installation

Place `moss_audio_8b_instruct_bf16.safetensors` in `ComfyUI/models/text_encoders/`. The tokenizer and required inference configuration are embedded; original HF shards are not required at inference.

| File | Size |
| --- | ---: |
| `moss_audio_8b_instruct_bf16.safetensors` | 18.110 GB |

Manifest/provenance files record the conversion and source revisions. `SHA256SUMS` and `FILES.json` describe this release. Filenames and model folders matter. No original source snapshot needs to be converted again.

## Usage

Select `moss_audio_8b_instruct_bf16.safetensors` in **Load CLIP**, type **moss_audio**. Connect CLIP to **Generate Text** and **Load Audio** to its audio input. Use a specific transcription, captioning or audio question prompt and an explicit output budget. Start with thinking disabled for this Instruct checkpoint; the control changes the prompt and is not a different set of weights. Select your own audio in the example.

Example graphs are in [workflows](workflows/README.md).

## Verification and limits

The package has pinned conversion provenance. Native Instruct participation in the Omni model-transition/lifecycle fixture is documented. The larger full-model caption/reference acceptance suite was conducted for Thinking and must not be assumed to validate this Instruct variant. This is a converted release with bounded variant acceptance. Exact timestamps, recognition accuracy, low-VRAM operation and other backends are not guaranteed.

These statements describe the linked retained tests, not a new cross-platform acceptance suite. File size is not a minimum RAM/VRAM requirement. No inference-time downloads or external inference worker are required by these native model paths.

## Conversion and provenance

Repackages the exact lakucho mirror revision, preserving 901 BF16 source tensors and embedding its tokenizer. This is an OpenMOSS model distributed via that mirror; it is not our fine-tune.

Source model revision: `8bd5b22c64dd80b59c06af4e3304e581a3e5596b`. See [PROVENANCE.json](PROVENANCE.json), the conversion manifest and [NOTICE](NOTICE). No training data, private inputs or generated user recordings are included.

## License and attribution

The pinned mirror model card declares Apache-2.0 and credits OpenMOSS. Both the actual source mirror and the original OpenMOSS authors are attributed.

See [LICENSE](LICENSE), [NOTICE](NOTICE), and the retained upstream model card/source notices. Model authors and publishers retain credit; this is a third-party ComfyUI repackaging and does not imply endorsement. The weights’ terms and the separately linked ComfyUI code license are distinct.

The example workflow files are copied/adapted from the linked ComfyUI fork; its GPL-3.0 license is retained in `LICENSES/COMFYUI-GPL-3.0.txt`. This does not relicense the model weights.