Skip to content
Agentmart
Submit a tool

AI agent tools for audio and video

In this catalog, an audio and video tool is one that transcribes, edits, generates or analyzes audio and video. Our enrichment pass tags 171 listings with it: 79 MCP servers, 73 agent skills, 3 plugins, 1 agent framework and 15 AI agents. By listing rank, the top MCP server is Vexa, the top agent skill is dbs-video-navigation and the top AI agent is ONCE. 20 of the 171 are published by the vendor behind the product, and 146 were active in the last 30 days. 11 of the 79 MCP servers run only as remote servers, with nothing to install locally. Each entry below links to its listing page, with grades, install commands and sources.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

What the job is

Tagged listings
171
By type
79 MCP servers, 73 agent skills, 3 plugins, 1 agent framework and 15 AI agents
Published by the vendor
20 of 171
Active in the last 30 days
146 of 171
Open source
140 of 171
MCP servers that run only remotely
11 of 79
Hosts named by the MCP servers
Claude Code (70), Cursor (70), VS Code (70)

Building blocks by type

The top entries of each type, by listing rank. Open a listing for its install command, grades and sources.

MCP servers 79 tagged

  1. 1
    Vexa

    vexa.aiOfficial

    Meeting bot and transcripts for Google Meet, Teams and Zoom.

    • Published by the vendor
    • 2.9K GitHub stars
    • Remote server, no local install

    ★ 2.9KLast active Oct 9, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  2. 2
    FFmpeg

    pollinations

    Trim, convert, resize, compress, and remix audio and video.

    • 5.2K GitHub stars
    • Remote server, no local install
    • Active in the last 30 days

    ★ 5.2KLast active Oct 24, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  3. 3
    FableCut

    ronak-create

    Zero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 746Last active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Claude Desktop +2

  4. 4
    Claude Real Video

    HUANGCHIHHUNGLeo

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

    • 2.3K GitHub stars
    • Most weekly downloads here (1.2K)
    • Active in the last 30 days

    ★ 2.3K↓ 1.2K/wkLast active Oct 8, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  5. 5
    FunASR

    modelscope

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

    • Most GitHub stars here (20,801)
    • Open source (MIT)

    ★ 20.8KLast active Sep 18, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Search MCP servers for audio and video → All connectors

Agent skills 73 tagged

  1. 1
    dbs-video-navigation

    dontbesilent2025

    根据本地视频或带时间戳字幕划分章节、话题或步骤，生成可导入剪辑软件的导航条 MP4、动态分段进度和时间表。用户要求视频章节导航、顶部进度条或当前位置提示时使用；不负责平台链接数据提取或标题封面开头文案。

    • Repository has 10.9K stars
    • Active in the last 30 days
    • Ships helper scripts

    ★ 10.9KLast active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    video

    coreyhaines31

    When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks.

    • Largest repository here (56,355 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 56.4KLast active Oct 19, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    cdf-augmentation

    NVIDIA <opensource@nvidia.com>

    Use when authoring or validating Cosmos Data Factory (CDF) augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls)…

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    jetson-video-pipeline

    Vinit Bansal <vinitkumarb@nvidia.com>

    Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode…

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Sep 25, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    nvidia-broadcast

    NVIDIA Broadcast Team <broadcast-skills-dev@nvidia.com>

    Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is…

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Oct 2, 2026Claude Code, Claude apps, Codex, Cursor +6

Search agent skills for audio and video → All skills

Plugins 3 tagged

  1. 1
    EchoVoice™

    PigonAI

    Text-to-speech for your AI coding partners — Claude Code, Codex, Gemini (Antigravity), and Kimi Code responses spoken aloud, each in its own voice.

    • Most GitHub stars here (2)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 2Last active Oct 13, 2026VS Code, Cursor, Windsurf, VSCodium

  2. 2
    Cloud TTS (Gemini / OpenAI / ElevenLabs)

    geryit

    Right-click selected text (editor or terminal) to read it aloud using a cloud TTS provider of your choice.

    • Open source (MIT)

    ★ 1Last active May 24, 2026VS Code, Cursor, Windsurf, VSCodium

  3. 3
    AI Voice Transcription for Cursor

    kdeosingh

    Talk directly to Cursor with your voice!

    • Open source (MIT)

    Last active Aug 19, 2025VS Code, Cursor, Windsurf, VSCodium

Search plugins for audio and video → All plugins

Agent frameworks 1 tagged

  1. 1
    Vision-Agents

    GetStream

    Python framework for real-time voice and vision agents that process video with pluggable models and processors over WebRTC.

    • 8.2K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 8.2K↓ 418/wkLast active Oct 24, 2026

Search agent frameworks for audio and video → All harnesses & sdks

AI agents 15 tagged

  1. 1
    ONCE

    ONCE

    ONCE is a music distribution agent.

  2. 2
    CWI Discovery Engine

    Cumulative Web Inc

    CWI Discovery Engine: MCP server for the Cumulative Web Inc music catalog.

  3. 3
    AudD Music Recognition

    AudD

    Identifies the song in an audio or video clip and returns artist, title, album, release date and streaming-service links.

  4. 4
    ClipTalk

    ClipTalk

    Make finished TikTok, Reels and YouTube videos from a prompt: script, AI visuals, voiceover, captions and music, rendered to a ready-to-post MP4.

  5. 5
    BibiGPT

    bibigpt.co

    AI 音视频知行助理 — Paste any video/audio URL (YouTube, Bilibili, podcasts, TikTok, X, Coursera, …) or upload a local file to get AI-powered summaries, transcripts…

Search AI agents for audio and video → All agents

Questions

What are the top tools for audio and video?
By listing rank, the top MCP server is Vexa, the top agent skill is dbs-video-navigation and the top AI agent is ONCE. Rank weighs adoption, freshness, documentation and publisher identity; money never changes it.
How many tools does the catalog list for audio and video?
171 listings are tagged for it: 79 MCP servers, 73 agent skills, 3 plugins, 1 agent framework and 15 AI agents. Tags come from an automated enrichment pass over the top-ranked listings, so tools outside that pass are not counted.
Which AI apps do the MCP servers work with?
Of the 79 MCP servers, 70 list Claude Code, 70 list Cursor and 70 list VS Code as a supported host. Open a listing for its install command and the other hosts it names.
Which of these are published by the vendor itself?
20 of the 171 are published by the vendor behind the product, including Vexa, dubbing and music.

171 listings are tagged for this use case; the lists above show the top entries.

Related