Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
FFmpeg
MCP serversTrim, convert, resize, compress, and remix audio and video.
-
Urantia Papers
Public APIsFull-text + semantic search across the Urantia Papers, with audio narration, entities, translations
-
Hugging Face
Public APIsAI model hub with inference API for NLP, computer vision, and audio
-
Sealed Rose
Public APIsAI media forensics and synthetic content verification for video, audio, image, and text
-
MiCompress
MCP serversCompress images, PDFs, video, audio, documents & archives via micompress.com
docker.io/huuhuybn/micompress-mcp:0.1.2 -
Subtly
MCP serversTranscribe audio and video, and translate subtitles into 50+ languages.
-
FFmpeg Micro
Public APIsHosted FFmpeg over REST: transcode, compress, trim and caption video, audio and images
-
nixamp
MCP serversNixamp audio and video player library and playlists (nixamp.com)
-
meshy-3d-agent
SkillsBuild Meshy 3D agent skills to generate, texture, rig, animate, and prep 3D models for print without an MCP server
git clone https://github.com/Laic-parsiism709/meshy-3d-agent.git -
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
openai/gpt-oss-safeguard-20b -
OpenAI: gpt-oss-120b (batch)
Modelsgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
openai/gpt-oss-120b:batch -
Google: Gemma 4 26B A4B
ModelsGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it -
Z.ai: GLM 4.5
ModelsGLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
z-ai/glm-4.5 -
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
qwen/qwen3-235b-a22b-thinking-2507 -
Cloud Speech-to-Text API
Public APIsConverts audio to text by applying powerful neural network models.
-
mcp
MCP serversConvert, compress, resize and trim images, audio, video and PDFs from local paths.
@formatika/mcp@0.1.2 -
Glif
MCP serversGenerate images, video, and audio with Glif's media-generation agent
-
SOAPNoteAPI
MCP serversGenerate clinical SOAP notes, billing codes, and visit summaries from transcripts or audio.
soapnoteapi-mcp@0.1.1 -
justcaptions
MCP serversAudio transcription, caption correction, translation and 16 video caption styles.
-
webear
MCP serversGive your AI coding assistant ears — capture, analyze, and describe live audio.
webear@1.2.4 -
whisper-mcp
MCP serversLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
whisper-mcp@0.1.1 -
viberadio-fm
MCP serversTurns an agent's output into audio: narration, podcast, or music.
viberadio-fm@0.2.3 -
MusicXML Synthesizer
MCP serversSynthesizes audio from MusicXML, with voice-part selection and tempo control
synth-mcp@0.2.3 -
Phishin
Public APIsA web-based archive of legal live audio recordings of the improvisational rock band Phish
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.