FunASR

Name: FunASR
Author: modelscope

torch · by modelscope

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

20.0k GitHub PyPI

11 open CVEs

MIT license

Actively maintained

Last commit 2d ago

Works with most clients

Transport: sse, http

0 tools

Grade F

MCPpedia last refreshed this data 12h ago

This server has been archived and is no longer actively maintained.

Edit this pageView history

FunASR is an MCP server that industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API. Its tool list has not been published yet over sse and http, requires no API key, and scores 33/100 on MCPpedia's security, maintenance and efficiency rubric.

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopsse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "funasr": {
      "args": [
        "torch"
      ],
      "command": "uvx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/funasr)](https://mcppedia.org/s/funasr)

Read me

What FunASR does

(简体中文|English|日本語|한국어)

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

33/100across 5 weighted dimensions

How we score →

0255075100

−67

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

11 open20 fixed

CVE-2025-3730low · fixedCVSS 3.3

PyTorch Improper Resource Shutdown or Release vulnerability

A vulnerability, which was classified as problematic, was found in PyTorch 2.6.0. Affected is the function torch.nn.functional.ctc_loss of the file aten/src/ATen/native/LossCTC.cpp. The manipulation leads to denial of service. An attack has to be approached locally. The exploit has been disclosed to the public and may be used. The name of the patch is 46fc5d8e360127361211cb237d5f9eef0223e567. It is recommended to apply a patch to fix this issue.

Affected: >= 0Fixed in 2.8.0source →

CVE-2026-4538highCVSS 7.8

PYSEC-2026-139

A vulnerability was identified in PyTorch 2.10.0. The affected element is an unknown function of the component pt2 Loading Handler. The manipulation leads to deserialization. The attack can only be performed from a local environment. The exploit is publicly available and might be used. The project was informed of the problem early through a pull request but has not reacted yet.

Affected: >= 0source →

CVE-2026-24747high · fixedCVSS 8.8

PYSEC-2026-2286

PyTorch is a Python package that provides tensor computation. Prior to version 2.10.0, a vulnerability in PyTorch's `weights_only` unpickler allows an attacker to craft a malicious checkpoint file (`.pth`) that, when loaded with `torch.load(..., weights_only=True)`, can corrupt memory and potentially lead to arbitrary code execution. Version 2.10.0 fixes the issue.

Affected: >= 0Fixed in 2.10.0source →

CVE-2025-63396lowCVSS 3.3

PYSEC-2025-210

An issue was discovered in PyTorch v2.5 and v2.7.1. Omission of profiler.stop() can cause torch.profiler.profile (PythonTracer) to crash or hang during finalization, leading to a Denial of Service (DoS).

Affected: >= 0source →

CVE-2025-55560high · fixedCVSS 7.5

PYSEC-2025-209

An issue in pytorch v2.7.0 can lead to a Denial of Service (DoS) when a PyTorch model consists of torch.Tensor.to_sparse() and torch.Tensor.to_dense() and is compiled by Inductor.

Affected: >= 0Fixed in 2.7.1source →

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is FunASR safe to use?: FunASR has 14 known CVEs tracked by MCPpedia. You can verify these on OSV.dev by searching for "torch". Review the Security section above for details before installing.
How do I install FunASR?: FunASR supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with FunASR?: FunASR is compatible with claude-desktop, cursor, claude-code. It uses sse and http transport.
Is FunASR actively maintained?: FunASR is actively maintained — last commit was 2 days ago. It has 20,025 GitHub stars.

Similar servers

Others in ai-ml

View all →

Dsh MCP Client97

MCP client bridge: connects to MCP servers and registers their tools on ctx.tools

196.7k 4

Gpt Researcher97

An autonomous agent that conducts deep research on any data using any LLM providers

29.2k 5

Modelcontextprotocol96

The official MCP server implementation for the Perplexity API Platform

2.5k 4

io.github.mims-harvard/tooluniverse96

1000+ scientific tools for AI scientists: life science, reserach, literature, and more.

1.7k 4

MCP Security Weekly

Get CVE alerts and security updates for FunASR and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Quick Start

No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.

# CPU-only installs can use the default PyPI wheels. pip install torch torchaudio pip install funasr

For GPU quickstarts, install the PyTorch and torchaudio wheels that match your NVIDIA driver from pytorch.org before installing FunASR. After installation, confirm the GPU is visible:

python - <<'PY' import torch print(torch.cuda.is_available()) PY

Only use device="cuda" when this prints True; otherwise use device="cpu" or reinstall PyTorch with the correct CUDA wheel.

Flagship model — Fun-ASR-Nano (LLM-ASR for Chinese, English, and Japanese, plus Chinese dialect groups and regional accents; needs a GPU):

from funasr import AutoModel model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda") result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav") print(result[0]["text"]) # 欢迎大家来体验达摩院推出的语音识别模型。

For the separate 31-language checkpoint, use Fun-ASR-MLT-Nano-2512. Language coverage is checkpoint-specific, so Nano and MLT-Nano should be treated as distinct model choices.

On CPU (or for five-language ASR plus emotion and audio-event tags), us

Frequently Asked Questions

Is FunASR safe to use?

FunASR has 14 known CVEs tracked by MCPpedia. You can verify these on OSV.dev by searching for "torch". Review the Security section above for details before installing.

How do I install FunASR?

FunASR supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with FunASR?

FunASR is compatible with claude-desktop, cursor, claude-code. It uses sse and http transport.

Is FunASR actively maintained?

FunASR is actively maintained — last commit was 2 days ago. It has 20,025 GitHub stars.

(简体中文|English|日本語|한국어)

Industrial speech recognition toolkit for offline, streaming, and edge deployment.
ASR · VAD · punctuation · speaker pipelines · emotion and audio-event models · OpenAI-compatible serving

Quick Start · Colab · Benchmark · Model selection · Migration guide · Use cases · Community integrations · Deployment matrix · Deployment hub · Troubleshooting · Models · Agent Integration · OpenClaw · Docs · Contribute

Quick Start

No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.

# CPU-only installs can use the default PyPI wheels.
pip install torch torchaudio
pip install funasr

For GPU quickstarts, install the PyTorch and torchaudio wheels that match your NVIDIA driver from pytorch.org before installing FunASR. After installation, confirm the GPU is visible:

python - <<'PY'
import torch
print(torch.cuda.is_available())
PY

Only use device="cuda" when this prints True; otherwise use device="cpu" or reinstall PyTorch with the correct CUDA wheel.

Flagship model — Fun-ASR-Nano (LLM-ASR for Chinese, English, and Japanese, plus Chinese dialect groups and regional accents; needs a GPU):

from funasr import AutoModel

model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda")
result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
print(result[0]["text"])
# 欢迎大家来体验达摩院推出的语音识别模型。

For the separate 31-language checkpoint, use Fun-ASR-MLT-Nano-2512. Language coverage is checkpoint-specific, so Nano and MLT-Nano should be treated as distinct model choices.

On CPU (or for five-language ASR plus emotion and audio-event tags), us

... View full README on GitHub