Skills and MCP tagged “audio”

media-use heygen-com skill Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs openai-whisper openclaw skill This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed. Claude Code CX Codex Cursor +1 7,100installs openai-whisper-api openclaw skill Runs audio through the OpenAI Audio Transcriptions API and returns text or JSON. Useful when you want a call or voice note transcribed without leaving the agent. Claude Code CX Codex Cursor +1 5,400installs sherpa-onnx-tts openclaw skill Offline text-to-speech CLI using sherpa-onnx without external cloud services. Converts text into WAV audio directly on your machine. Claude Code CX Codex Cursor +1 5,300installs blucli openclaw skill This skill gives your agent the blu command for Bluesound and NAD players: discovery, playback, grouping and volume. Claude Code CX Codex Cursor +1 5,100installs songsee openclaw skill Turns an audio file into a spectrogram or a feature panel with mel, chroma, MFCC and more. Useful when you want to see a track instead of just hearing it. Claude Code CX Codex Cursor +1 5,100installs gemini-live-api-dev official google-gemini skill Guides real-time bidirectional streaming development with the Gemini Live API and migration to Gemini 3.8 Live. Claude Code CX Codex Cursor +1 10,200installs speech official openai skill Generates voiceovers, narration, and IVR audio clips via OpenAI Audio API. Useful when your project needs spoken audio files from plain text. Claude Code CX Codex Cursor +1 3,500installs transloadit-media-processing official github skill Process video, audio, images and documents through Transloadit. Use it to encode media, make thumbnails or extract text from scanned files. GitHub Copilot 8,700installs speech nexu-io skill Generates spoken audio from text using OpenAI's API and built-in voices. Handy for narrated explainers, lecture audio, and quick voiceover tracks. Claude Code CX Codex Cursor +1 2,700installs venice-audio-music nexu-io skill Queues and retrieves music generation jobs through Venice.ai endpoints. Built for short jingles, background loops, and prototype scoring. Claude Code CX Codex Cursor +1 2,700installs resemble-detect official github skill Detects synthetic audio, images, video, and text using Resemble AI. Helpful for media verification, watermark detection, and voice provenance checks. GitHub Copilot 68installs speak-summary official github skill Rewrites written notes or summaries into listenable spoken prose and synthesises an MP3 file locally on CPU using Kyutai pocket-tts without cloud services. GitHub Copilot 12installs