Media & Streaming

This skill enables agents to process voice messages by transcribing them to text and generating spoken replies using local software.

This skill automates playing a poker game called MOPO by interacting with an external game server.

This skill generates retro robotic speech audio from text using the classic SAM text-to-speech engine, allowing for voice messages and a mode where all responses are spoken robotically.

Fetches news and flash updates from MarsBit using their hosted API.

Manages financial accounts by checking balances, topping up funds, and handling API keys.

This skill provides a command-line interface for controlling BluOS devices, allowing for discovery, playback, and grouping of audio streams.

This skill is designed to generate text-to-speech, sound effects, and music.

Generates AI images, videos, music, and audio from your terminal using various AI models.

This skill allows you to edit and enhance images and videos using AI-powered tools through the muapi.ai service, offering features like prompt-based editing, upscaling, and background removal.

This skill helps you create multiple accounts for emails and social media platforms in bulk.

This skill helps you create, schedule, and optimize social media content for various platforms like LinkedIn, Twitter/X, Instagram, TikTok, and Facebook.

This skill helps you master audio files using command-line tools, improving their sound quality and converting them to different formats like WAV or MP3.

This skill helps you generate content for Chinese social media platforms like Xiaohongshu, Zhihu, WeChat Official Accounts, and Douyin, including formatting, hooks, and calls to action.

This skill automatically gathers and summarizes news and updates from the media and entertainment industry, including box office, streaming, and awards.

This skill converts Chinese text into spoken audio using the UniSound TTS service.

This agent analyzes and executes trades on the Kalshi prediction market.

This skill allows you to use your computer's built-in text-to-speech (TTS) functionality directly from the command line, enabling spoken output for various phrases and scenarios.

Helps you find podcasts and episodes and generate links to listen to them on wherever.audio.

This skill converts voice messages and audio files into text using an offline speech recognition tool.

This skill allows users to access and retrieve real estate listing data from CREA/REALTOR.ca for research and automation purposes.

This skill automatically transcribes YouTube videos, first by checking for existing subtitles and then by downloading audio and using the OpenAI Whisper API if subtitles are unavailable.

This skill helps you create podcasts, explainer videos, or voice narrations from text, URLs, or topic descriptions.

This skill helps you find real estate properties that are already being rented out on Airbnb.

This skill helps you download videos, playlists, and audio from YouTube and other websites using the yt-dlp tool.