Create images, video and music

Tool

PaperBanana

Generative MediaResearch

llmsresearch

PaperBanana wraps gpt-image-1.5 or gemini-3-pro-image-preview in a 7-agent loop: retrieve 13 reference figures, plan the

diagram-generationacademic-figuresmulti-agentgemini

Tool

SwarmUI

Coding

mcmonkeyprojects

Modular web UI for AI image and video generation, with an accessible generate tab and a raw Comfy node graph

stable-diffusioncomfyuiguinode-graph

Tool

TwelveLabs

MemoryData Wrangling

twelvelabs-io

Video intelligence API (Marengo embeddings, Pegasus video-language model) with SDKs and MCP integration for video search and reasoning.

videomultimodalvector-dbvideo-searchsdk

Tool

OrkasVideoStudio

Generative MediaVoice

Orkas-AI

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

motion-graphicsffmpegmcp-servercoding-agent

Framework

OpenMontage

Generative MediaCoding

calesthio

Agentic video production system that drives an AI coding assistant through scripting, asset generation, editing, and rendering

videoffmpegremotionttsstable-diffusion

Tool

MiniMax-MCP

VoiceGenerative Media

MiniMax-AI

Official MCP server exposing MiniMax text-to-speech, voice cloning, image and video generation APIs to MCP clients.

mcp-serverttsvoice-cloning

Tool

Neuphonic

VoiceGenerative Media

neuphonic

Text-to-speech via Neuphonic's API.

ttsvoice-cloningon-devicegguf

Tool

Chatterbox

VoiceGenerative Media

resemble-ai

Open zero-shot voice-cloning TTS family with multilingual, low-latency Turbo, and CPU-scale Nano variants

ttsvoice-cloningmultilingualzero-shot

Tool

Video Use

Generative MediaVoice

browser-use

Edit videos with coding agents — drop raw footage in a folder, chat, get final.mp4.

videoffmpegremotionelevenlabs

Tool

ChatTTS

VoiceGenerative Media

2noise

Generative text-to-speech for dialogue in English and Chinese, with multi-speaker output and prosody control

ttsmultilingualprosody-controldialogue

Tool

Guizang PPT Skill

Generative Media

op7418

Agent skill that generates single-file HTML slide decks in magazine or Swiss layouts, plus images and social covers

productivityhtml-deckpresentationswiss-designcodex

Tool

Inworld

VoiceGenerative MediaTraining

inworld-ai

Realtime speech-to-speech and expressive TTS-2 text-to-speech.

ttsfine-tunespeech-to-speechreal-time

Tool

Pireel

Generative MediaInterface

pireel

The open-source alternative to Capcut、ChatCut. Drivable by any AI agent over MCP.

videocaptionsavatarcanvas

Tool

Skill Autoshorts

ConnectorsGenerative Media

mutonby

Agent skill that cuts long vertical videos into short clips with a chat approval step, then schedules them to TikTok, Instagram, and YouTube

videoproductivitytiktokinstagramyoutubeffmpeg

Tool

Video Report Nemotron

Data WranglingVoice

AetherX-Technologies

Hermes skill that turns videos into Markdown, HTML, and PDF reports, using subtitles first and local Nemotron ASR as fallback

videoproductivitynemotronsttmlx

AI Coustics

Voice

Real-time speech enhancement and standalone voice-activity detection for agent audio streams.

audiospeech-enhancementvoice-activity-detectionreal-timeaudio-processing

App

Airi

VoiceGenerative Media

moeru-ai

Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds.

avatarlive2dai-companioncharacter-ai

Tool

Anam

VoiceGenerative Media

Real-time video-avatar service synchronising audio and video.

videoavatarlip-syncreal-timechatbot

Async

VoiceGenerative Media

Text-to-speech via Async's WebSocket and HTTP APIs.

ttswebsocketreal-timelow-latency

AWS Polly

VoiceGenerative Media

Text-to-speech via Amazon Polly.

ttscloudmultilingual

Beyond Presence

VoiceGenerative Media

Real-time video-avatar transport for voice agents.

videoavatarreal-timelivekit

Cartesia

VoiceGenerative Media

Real-time speech-to-text and text-to-speech via Cartesia's streaming APIs.

ttssttreal-timestreaming

Chert

Voice

Vapi for FaceTime: AI video agents in a few lines

videofacetimevideo-callingremote-supportonboarding

Daily

Voice

WebRTC transport for real-time audio/video agent communication.

videowebrtcpipecatreal-time