Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
agent-media-toolkit
MCP servers15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more.
-
thursday-agent
SkillsTalk, and a team of bots does the work in a real browser, a shell and your files while she keeps talking. Open source, runs on your machine, on your ChatGPT plan or an OpenAI key. npx thursday-agent
git clone https://github.com/cgoinglove/thursday-agent.git -
BananaBanana Image, Video & Speech Generation
MCP serversImages, video & speech: Nano Banana, GPT Image, Veo, Omni, Wan, Grok, Gemini TTS. Crypto or card.
-
Cloud Speech-to-Text API
Public APIsConverts audio to text by applying powerful neural network models.
-
lemo-opuscar
SkillsA toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:66 种现成风格,也能做出你自己的
git clone https://github.com/lemomo-ai/lemo-opuscar.git -
quackd
Agents & frameworksThe communication layer between people and robots, and between robots. Talk to any robot in your own words, with an LLM for its brain. Robots that have never met check each other's passports and share the work. Microduck, Huebot, Open Duck Mini, LeRobot arms, XLeRobot carts, AlohaMini, ToddlerBot, MOSS, ROS bases and industrial arms on ROS 2.
git clone https://github.com/rokbenko/quackd.git -
lizheng-open-context
AI repositoriesSource-grounded public context for 立正: Superlinear posts, selected comments, YouTube, Public Axioms V1, and 《真本事》.
git clone https://github.com/sunyuzheng/lizheng-open-context.git -
YouTube transcripts with timestamps, title and channel, via residential proxy (no cloud-IP blocks).
-
SuperClonica text to speech
MCP serversText to speech in about 190 voices and 31 languages: offline on your computer or via the cloud.
superclonica-mcp@0.1.0 -
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
-
Presentr Analyze
MCP serversRead text aloud in 48 languages, transcribe audio, extract and translate PDF text, dub video.
-
convert.express
MCP serversTranscribe audio and video to text, SRT or VTT. Summaries, translation. Optional OAuth sign-in.
-
GrooveSheet
MCP serversFind AI-transcribed sheet music, MIDI and stems for songs. /mcp/public needs no sign-in.
-
WACrew · WhatsApp MCP server
MCP serversWhatsApp MCP server: read chats and groups, transcribe voice notes and reply at a human pace.
wacrew-mcp@0.1.3 -
ai-skills
Skills24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, TTS, DevOps, and Google Workspace
git clone https://github.com/sanjay3290/ai-skills.git -
LFM3-Audio-2B-GGUF
Modelsany to any model by LiquidAI · gguf
LiquidAI/LFM3-Audio-2B-GGUF -
Czech audio/video transcription: upload media, run transcription, get transcript and QA report.
-
omnilingual-asr-corpus
Datasets & benchmarksHugging Face dataset by facebook
facebook/omnilingual-asr-corpus -
I want you to act as a speech-language pathologist (SLP) and come up with new speech patterns, communication strategies and to develop confidence in their ability to communicate without stuttering. You should be able…
-
One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.
-
TidyTools Free Web Data
MCP servers45 free keyless web tools: AI extract, OCR, transcribe, SEO, DNS, contacts. Strict daily limits.
-
Track Podcasts
MCP serversWho sponsors which podcasts, from transcribed ad reads. Free: 10 calls/day with no key, 25 with one.
-
youtube-transcripts
MCP serversYouTube transcripts with timestamps from video links or channels. Charged only per transcript.
-
YouTube Transcripts & Creator Data
MCP serversYouTube transcripts, channel transcripts, comments and public creator business emails.
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.