io.github.modelscope/funasr-mcpmedia

FunASR

Verified · 24 days ago

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

Install

claude mcp add funasr-mcp -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2

Our take

FunASR is a local speech-to-text server for transcribing audio with on-device models, including SenseVoice-style workflows. It fits users who want private transcription without sending media to a hosted API, especially for offline or sensitive workloads. The quality signal is strong on project visibility and apparent adoption, though local-model setup still makes it more technical than plug-and-play SaaS connectors.

reviewed by hand · 2026-07-24

Something wrong or dead here? Report it

Verification record

last verified
24 days ago
github stars
20k
last commit
24 days ago
archived
no
license
MIT
in registry since
2026-07-26

github.com/modelscope/FunASR

Figma-Context-MCPmedia

Figma-Context-MCP

Verified · 26 days ago

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

hand-reviewed16k stars95k dl/wkchecked 26 days ago

openshortsmedia

openshorts

Verified · 9 days ago

Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.

hand-reviewed3.7k starschecked 9 days ago

claude-real-videomedia

claude-real-video

Verified · 9 days ago

Let any LLM watch a video locally — and search everything it has ever watched.

hand-reviewed2.1k starschecked 9 days ago

Figma MCP Server

Verified · yesterday

The Figma MCP server brings Figma design context directly into your AI workflow.

hand-reviewed2.0k starschecked yesterday

voicemodemedia

voicemode

Verified · yesterday

Natural voice conversations for AI assistants - STT/TTS via MCP

hand-reviewed1.3k starschecked yesterday

openbrandmedia

OpenBrand

Verified · 23 days ago

Extract brand assets (logos, colors, backdrop images, brand name) from any website URL

hand-reviewed783 stars33 dl/wkchecked 23 days ago