npm

Search results

77 packages found

A library providing an API for generating MIDI files.

published version 3.2.1, 4 months ago25 dependents licensed under $MIT
31,205

Zero-setup durable creative-media CLI for agents (image + video + audio + 3D): guide-first creation, model and cost inspection, owned URLs, JSON recovery, payments, reusable assets, and feedback.

published version 0.1.65, 3 hours ago0 dependents licensed under $MIT
7,958

Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code

published version 1.22.4, 2 days ago0 dependents licensed under $MIT
4,543

Sogni Creative Agent Skill: agent skill and CLI for Sogni AI image, video, and music generation.

published version 3.6.1, 2 days ago0 dependents licensed under $MIT
2,528

The creative toolkit for AI agents — generate images, video, voiceover, music, sound effects, and full podcasts from the command line.

published version 3.2.0, 2 days ago0 dependents licensed under $MIT
3,663

n8n nodes for Google AI Studio WolfHub: Music (Lyria), Speech TTS, Images (Imagen), Videos (Veo)

published version 1.1.7, 9 days ago0 dependents licensed under $MIT
2,841

MCP server for Kie.ai APIs: image, video, music and speech generation across Nano Banana, Veo3, Suno, ElevenLabs, ByteDance, Qwen, Runway, Midjourney, Wan, Hailuo, Kling, GPT Image 2, Flux Kontext, Recraft, Ideogram, Topaz, HappyHorse and more.

published version 3.5.0, 10 days ago0 dependents licensed under $MIT
2,370

Model Context Protocol server for AetherWave Studio - one tool surface for music, image, video, and audio generation across Suno, Grok Imagine, Seedance, Kling, Hailuo, Wan, VEO, Ideogram, GPT Image 2, and more.

published version 0.2.6, 5 days ago0 dependents licensed under $MIT
2,001

Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.

published version 0.0.17, a year ago1 dependents licensed under $MIT
1,509

n8n community node for Kie.ai API - Image, Video, and Music generation

published version 1.0.10, a month ago0 dependents licensed under $MIT
1,224

AI video generation SDK — JSX for videos. Generate, compose and render AI videos with Kling, Flux, ElevenLabs, and more through one API. Built on Vercel AI SDK.

published version 0.4.0-alpha113, 2 months ago0 dependents licensed under $Apache-2.0
885

First-party LLM gateway SDK for apps generated on the VibeX platform — chat, streaming, image, video, music (Lyria), sound effects (ElevenLabs) and embeddings without shipping any third-party API key.

published version 1.1.0, 6 days ago0 dependents licensed under $MIT
1,129

ElevenLabs speech-to-text, text-to-speech, and music-generation provider for @effect-uai/core.

published version 0.8.0, 8 days ago0 dependents licensed under $MIT
900

MCP server for multimodal generation: MiniMax (TTS/Image/Video/Music) + MiMo (TTS)

published version 1.0.4, 10 days ago0 dependents licensed under $MIT
644

Standalone CLI for Kie.ai APIs: generate images, video, music and speech from the terminal. Same models as the Kie.ai MCP server, no MCP client required.

published version 0.2.0, 12 days ago0 dependents licensed under $MIT
540

MCP server for GlianaAI — pay-per-call generative AI across 59 models (image, video, music, speech). No signup or API key; each generate is paid per call from your own wallet over MPP / x402.

published version 0.3.4, 11 hours ago0 dependents licensed under $MIT
763

MCP server for Kie.ai. Sync-wait, auto-download, batch compare, cost telemetry, local-file upload. Umbrella tools (kie_image, kie_video, kie_music, kie_speech, kie_compare, kie_upload) dispatch across 30+ providers.

published version 0.2.1, 17 days ago0 dependents licensed under $MIT
581

MCP server for AI media generation in Remotion projects - images, videos, music, sound effects, speech, and subtitles

published version 1.2.2, 4 months ago0 dependents licensed under $MIT
401

MCP server (unofficial, fan project) for AI-assisted live-coding music via strudel.cc. Lets Claude drive pattern generation, audio analysis, and MIDI export through the Strudel browser REPL.

published version 4.0.0, a month ago0 dependents licensed under $AGPL-3.0-or-later
392

OpenClaw provider plugin for Ace Data Cloud — chat, image, video, music, and web-search across 50+ AI models through a single OpenAI-compatible endpoint.

published version 2026.5.34, 4 days ago0 dependents licensed under $MIT
437