Browse skills

Transloadit Media Processing efficiently converts and optimizes various video/audio formats for seamless playback across different platforms – a vital tool for content creators.

This skill generates human-like text responses from audio input, enabling voice-based interactions and content creation.

Transcribe converts audio or video into editable text, streamlining content creation and making spoken words searchable and usable.

Generates custom images, documents, code snippets, or audio files based on detailed user prompts and specifications.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.

This skill converts written text into natural-sounding speech, enhancing accessibility and creating engaging audio experiences.

Converts spoken audio into written text instantly, boosting accessibility and streamlining transcription workflows for various applications.

This skill generates realistic sound effects using ElevenLabs, enhancing audio content for immersive experiences and creative projects.

This skill uses ElevenLabs to generate realistic audio of musical pieces, enhancing creative projects and providing engaging auditory experiences.