Skill UI

A comprehensive guide for migrating and integrating with the Wispr Flow voice-to-text API. This skill details best practices for both WebSocket (low-latency streaming) and REST API methods. It covers authentication, optimal audio formatting (16kHz mono PCM), context awareness for specialized jargon (e.g., code), and robust error handling across multiple platforms (Mac, iOS, browser).

A comprehensive guide for integrating the Wispr Flow voice-to-text API using webhooks. This skill covers best practices for real-time speech recognition, including low-latency WebSocket streaming and robust REST API calls. It is essential for developers building voice-powered applications, dictation tools, or any system requiring advanced audio processing and context-aware transcription.

Generate professional and modern presentations using the 2slides AI API. This tool supports creating decks from raw text, matching a specific design style via a reference image, summarizing documents, adding AI voice narration, and exporting results as PDFs or images. Use it for any 'make slides' or 'create a deck' request.

This tool parses a structured, multi-shot video script (following the ai-video-script format) and automatically generates a time-coded SRT subtitle file. It calculates cumulative timestamps based on the duration of each shot, ensuring accurate subtitle cues that sync with the voiceover content across the entire sequence. Ideal for the post-production stage of short-form video creation.