Skill UI

Client library for Azure OpenAI and OpenAI services in .NET, covering chat completions, embeddings, image generation, audio transcription, and assistants with API key or Entra ID auth.

Python client library for Azure AI Transcription (speech-to-text). Supports real-time and batch transcription with timestamps, diarization, and locale specification. Ideal for meeting transcription, subtitle generation, and audio analysis.

A Python-based REST API skill for Azure Speech to Text, enabling simple speech recognition of short audio files (up to 60 seconds) without using the Speech SDK. It covers setup, authentication, request formats, and chunked transfer for efficient transcription.

Integrate the Modellix API/CLI for asynchronous AI image, video, and speech generation or transcription. Use the official CLI workflow (model run --wait, task download) to generate images, videos, speech, transcribe audio, and clone voices with models like Nano Banana, Seedance, Whisper, and CosyVoice.

This skill enables the transcription, display, and animation of captions within Remotion projects. It requires captions to be processed in JSON format using the specific Caption type. Users can generate captions from video/audio, display them in the final video, or import existing .srt files. It is suitable for video production workflows requiring automated or structured subtitle integration.