Skill UI

OpenAI’s Whisper provides robust multilingual speech-to-text transcriptions, translations to English, and language detection across 99 languages, suitable for podcasts, meetings, and noisy audio workflows with CPU/GPU acceleration and batch or streaming modes.

Arboreto infers gene regulatory networks from bulk or single-cell RNA-seq data using scalable GRNBoost2 and GENIE3 algorithms, letting researchers filter transcription-factor targets, run distributed Dask jobs, and export ranked links for downstream analysis.

MarkItDown converts PDFs, DOCX, PPTX, XLSX, HTML, JSON, XML, archives, YouTube links, images via OCR, and audio via transcription into clean Markdown, providing token-efficient text ready for LLMs and documentation workflows.

This comprehensive skill provides an end-to-end solution for video and audio content creation. Users can upload videos from various sources (YouTube, local files) and perform advanced operations such as real-time streaming, semantic search, and complex editing (trimming, overlays). Key features include AI-powered transcription, subtitle generation, and the ability to generate diverse media assets like images, music, sound effects, and voiceovers, making it ideal for content creators and media professionals.

Enables an OpenClaw agent to place managed outbound phone calls for alerts, briefings, reminders, and urgent notifications without Twilio, combining REST-triggered dialing with transcription and TTS so conversations feel like chat.

Arboreto infers gene regulatory networks from bulk or single-cell RNA-seq data using scalable GRNBoost2 and GENIE3 algorithms, letting researchers filter transcription-factor targets, run distributed Dask jobs, and export ranked links for downstream analysis.

MarkItDown converts PDFs, DOCX, PPTX, XLSX, HTML, JSON, XML, archives, YouTube links, images via OCR, and audio via transcription into clean Markdown, providing token-efficient text ready for LLMs and documentation workflows.

This guide provides comprehensive instructions for setting up the AssemblyAI SDK in both Node.js and Python environments. It covers package installation, secure API key management using environment variables, and client initialization for utilizing transcription and streaming services.

A comprehensive setup guide for establishing a fast, reproducible local development environment for AssemblyAI projects. It incorporates hot reloading, local caching of transcription results, and mocked testing utilities to ensure rapid iteration cycles without relying on live API keys or incurring costs. Ideal for setting up new services or enhancing existing AI workflows.

This workflow provides comprehensive audio processing capabilities, covering both real-time streaming transcription (for live captions and voice agents) and advanced post-processing using LeMUR. Use it for summarizing long meetings, answering questions based on transcripts, extracting action items, and running custom LLM analyses on recorded audio.

This skill provides a comprehensive guide to optimizing costs when using AssemblyAI for speech-to-text transcription. It details model selection (Best vs. Nano), guides feature budgeting (e.g., Diarization, Sentiment Analysis), and includes code examples for cost estimation and usage tracking. Use this when managing billing, reducing operational expenses, or implementing budget alerts for high-volume audio processing.

This guide provides comprehensive instructions for deploying AssemblyAI-powered transcription services to major cloud platforms like Vercel, Google Cloud Run, and Fly.io. It covers essential steps including secure secret management, setting up webhook endpoints for asynchronous notifications, and implementing streaming token endpoints for real-time client use in production environments.