Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Sport Vision
Public APIsIdentify sport, brands and gear in an image. Also does image sports captioning
-
JoyVASA
AI repositoriesDiffusion-based Portrait and Animal Animation
git clone https://github.com/jdh-algo/JoyVASA.git -
SmartCompanion
MCP serversCreate and edit museum audioguide apps: stations, tours, texts, images, audio and app design.
-
Official Le Scribe Audio MCP server: search, read, summarize & code French audio transcripts.
-
LTX-Video
Modelsimage to video model by Lightricks · diffusers
Lightricks/LTX-Video -
OpenAI: GPT-5.4 Nano (batch)
ModelsGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
openai/gpt-5.4-nano:batch -
“I want you to analyze the videos and images I upload and recreate the exact same style. Give me outputs like example voice, dialogue delivery, video style, dialogue delivery format, 4K aspect ratio exatra exatra, and…
-
skills
SkillsVideo skills for Claude Code, Codex, Grok, Cursor and Gemini CLI: 83 AI video skills for UGC ads, product videos, music videos, consistent characters, captions, motion graphics and FFmpeg edits. Seedance 2.5, Kling 4, Veo 3.1, GPT Image 2.6 and ElevenLabs on one key, or free and local.
git clone https://github.com/vargHQ/skills.git -
Speechmatics MCP by usefulapi
MCP serversTranscribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
-
convert.express
MCP serversTranscribe audio and video to text, SRT or VTT. Summaries, translation. Optional OAuth sign-in.
-
MoonshotAI: Kimi K2.6
ModelsKimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
moonshotai/kimi-k2.6 -
Perplexity: Sonar
ModelsSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
perplexity/sonar -
vision-squeezer
MCP serversShrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.
vision-squeezer@0.9.0 -
dsh-media-skills
SkillsFree image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.
git clone https://github.com/MJorgin/dsh-media-skills.git -
Audio & Video Transcription (Whisper)
MCP serversWhisper transcription of audio, video and podcast feeds, via the Apify actor
-
musicgen-large
Modelstext to audio model by facebook · transformers
facebook/musicgen-large -
csm-1b
Modelstext to speech model by sesame · transformers
sesame/csm-1b -
higgs-tts-2-3b-base
Modelstext to speech model by bosonai · transformers
bosonai/higgs-tts-2-3b-base -
TangoFlux
AI repositories[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
git clone https://github.com/declare-lab/TangoFlux.git -
Nativ
MCP serversLocalize text, images, audio and subtitles with brand voice, memory and style guides.
nativ-mcp@0.5.2 -
AgentCompute
MCP serversShared GPU beta: account API/MCP, task catalog, text, images and audio. Capacity varies.
-
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...
prism-ml/ternary-bonsai-2-27b -
musicgen-small
Modelstext to audio model by facebook · transformers
facebook/musicgen-small -
image-to-video
Tools & appsHugging Face space by thea2026
thea2026/image-to-video
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.