v1.3.26

modelscope/FunASRv1.3.26Jul 22, 2026by github-actions[bot]

AI Summary

Maintenance release focusing on honoring the server hub for default Nano models and updating documentation for community integrations.

Key Highlights

Honors server hub for default Nano model selection
Adds voice input community integrations documentation
Promotes merged Chinese LLM resource listing
Includes runtime downloads for llama.cpp v0.1.8

New Features

Server hub support for default Nano
Voice input integration docs
Chinese LLM resource listing
Runtime v0.1.8 updates

Full Release Notes

## What's Changed
* docs: require FunASR 1.3.25 for Nano guides by @LauraGPT in https://github.com/modelscope/FunASR/pull/3319
* docs: add voice input community integrations by @LauraGPT in https://github.com/modelscope/FunASR/pull/3320
* docs: promote merged Chinese LLM resource listing by @LauraGPT in https://github.com/modelscope/FunASR/pull/3322
* chore: classify external review wait states by @LauraGPT in https://github.com/modelscope/FunASR/pull/3323
* fix: honor server hub for default Nano model by @LauraGPT in https://github.com/modelscope/FunASR/pull/3324
* chore: release FunASR 1.3.26 by @LauraGPT in https://github.com/modelscope/FunASR/pull/3325


**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.3.25...v1.3.26

## Runtime downloads

This Python release pairs with the current prebuilt llama.cpp / GGUF runtime release: [runtime-llamacpp-v0.1.8](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.1.8).

Use these assets when you want the self-contained `llama-funasr-*` binaries instead of the Python package. The runtime release is shared by the current Python releases; `v1.3.26` itself is the PyPI package release.

| Platform | Asset | SHA-256 |
|---|---|---|
| Linux arm64 | [funasr-llamacpp-linux-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-linux-arm64.tar.gz) | `208752f36745700eaba91698f9d1e93df7b29d692b63a620483e7419480ece66` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-linux-x64-avx2.tar.gz) | `a92f9910ac226985f3147ebbbaf3e65d6372b30914b2fd02674fcec2304d9074` |
| Linux x64 Vulkan | [funasr-llamacpp-linux-x64-vulkan.tar.gz](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `bc679446ee962b745cb4be30d10a14a60772349299d1756bfd09d4575b1c1827` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-linux-x64.tar.gz) | `e10264253505250a16a369486623378a002d16034fa522163d01371e5657e955` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-macos-arm64.tar.gz) | `cf2da7dbcaaff40d15179e1ec1981da6cff60305a229bb3e0f67039f2e5b6f01` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-windows-x64-avx2.zip) | `717edaddc33d26cda60594262077a8573c52c96784fed9f4ee82cf8154a53935` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-windows-x64-cuda.zip) | `b26fd7557032565af97d4fda9ca447db6b1af72925a6ba2ba7dbc01a1cfd05a7` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/runtime-llamacpp-v0.1.8/funasr-llamacpp-windows-x64.zip) | `e390fe2ca46c3554d0ea04832f5804f82a8c427c815eb9e7c7e9954d7cc5866b` |

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==1.3.26"
```