v1.4.13

modelscope/FunASRv1.4.13Sep 2, 2026by github-actions[bot]

AI Summary

This release introduces support for n8n OpenAI audio transcription, fixes issues related to ONNX runtime dependencies and NumPy 2 ABI mismatches, and improves real-time VAD handling. It also includes documentation updates and new runtime downloads for various platforms.

Key Highlights

Added support for n8n OpenAI audio transcription in the server.
Fixed ONNX runtime dependency error handling and normalized ISO language hints.
Addressed NumPy 2 ABI compatibility issues and partial VAD overrun in real-time mode.
Added offline vLLM example for Qwen3-ASR.

New Features

Server: Support n8n OpenAI audio transcription
qwen3-asr: Add offline vLLM example

Full Release Notes

## What's Changed
* docs: align localized deployment release references by @LauraGPT in https://github.com/modelscope/FunASR/pull/3614
* fix(onnx): preserve missing runtime dependency errors by @LauraGPT in https://github.com/modelscope/FunASR/pull/3605
* fix(fun-asr-nano): normalize ISO language hints by @LauraGPT in https://github.com/modelscope/FunASR/pull/3613
* feat(server): support n8n OpenAI audio transcription by @LauraGPT in https://github.com/modelscope/FunASR/pull/3612
* fix(realtime): accept bounded partial VAD overrun by @LauraGPT in https://github.com/modelscope/FunASR/pull/3591
* fix: prevent NumPy 2 ABI mismatches by @LauraGPT in https://github.com/modelscope/FunASR/pull/3615
* docs: clarify native vLLM transcription path by @LauraGPT in https://github.com/modelscope/FunASR/pull/3603
* docs: surface MOSS in use-case selection by @LauraGPT in https://github.com/modelscope/FunASR/pull/3608
* docs: clarify Fun-ASR-Nano HF CTC boundary by @LauraGPT in https://github.com/modelscope/FunASR/pull/3609
* docs: add Open WebUI MOSS service recipe by @LauraGPT in https://github.com/modelscope/FunASR/pull/3607
* docs(vllm): add measured L20 tuning profile by @LauraGPT in https://github.com/modelscope/FunASR/pull/3598
* docs: clarify MOSS speaker-label boundaries by @LauraGPT in https://github.com/modelscope/FunASR/pull/3590
* docs: surface current runtime packages in ja and ko by @LauraGPT in https://github.com/modelscope/FunASR/pull/3604
* feat(qwen3-asr): add offline vLLM example by @LauraGPT in https://github.com/modelscope/FunASR/pull/3592
* docs: make the roadmap actionable by @LauraGPT in https://github.com/modelscope/FunASR/pull/3593
* docs: refresh ecosystem growth snapshot by @LauraGPT in https://github.com/modelscope/FunASR/pull/3606


**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.4.12...v1.4.13

<!-- funasr-runtime-downloads:start -->
## Runtime downloads

This Python release pairs with the current prebuilt llama.cpp / GGUF runtime release: [runtime-llamacpp-v0.2.6](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.6).

The same verified runtime assets are attached directly to this Python release so users can find the package and self-contained `llama-funasr-*` binaries in one place.

| Platform | Asset | SHA-256 |
|---|---|---|
| Linux arm64 | [funasr-llamacpp-linux-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-linux-arm64.tar.gz) | `7bca29cfa3c9a08e235a62212ca9e00f6656e59a8f07078966a2bfda1e5aa1f9` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-linux-x64-avx2.tar.gz) | `aaebc5470f846ce915200b35d6e9f9bd0a0d3ed399d39e49bdeb7a1f1782bc70` |
| Linux x64 Vulkan | [funasr-llamacpp-linux-x64-vulkan.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `f02d41e98e9d4041f0896661007193810f025484d2175958f7c1313d5c90ec46` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-linux-x64.tar.gz) | `779967de1c528c2be966bcc47f246e7d3e6fcdb748d9491263062f4120f35e52` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-macos-arm64.tar.gz) | `bda59474202b887190f59d25b7b42c714469efae71276072c12fa0a38de68792` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-windows-x64-avx2.zip) | `062cda8fefadd31c3e811227116daccf448a8520f4b0bb168d225c896e65ebbd` |
| Windows x64 CUDA Blackwell (sm_120) | [funasr-llamacpp-windows-x64-cuda-blackwell.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-windows-x64-cuda-blackwell.zip) | `e32961a753f40888182f352fa551159c5165a6a77718ae4ade316aedfea4b1c2` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-windows-x64-cuda.zip) | `148657911fb666b7af6ec43af2e23a0984e3259012b4c39f95631b717feb6840` |
| Windows x64 Vulkan | [funasr-llamacpp-windows-x64-vulkan.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-windows-x64-vulkan.zip) | `debf8007e55011cad06081e7b8a78972f1b8fe672bc324d41e650d68821f6a6a` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.13/funasr-llamacpp-windows-x64.zip) | `f6a73a548413ba9fbaf2145263ea66ec53cbdad1fb11790dbeeee493e339492e` |

Quick start: download one asset, unpack it, then run the bundled `download-funasr-model.sh <sensevoice|paraformer|nano>` helper and one of `llama-funasr-cli`, `llama-funasr-sensevoice`, or `llama-funasr-paraformer`.

For Python users, install from PyPI:

```bash
python -m pip install -U "funasr==1.4.13"
```
<!-- funasr-runtime-downloads:end -->