Browse skills

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

Transcribe audio and video files to text using OpenAI Whisper. Supports 50+ languages with automatic language detection.

Whisper Transcription — provides AI agent assistance for software development workflows.

Provides automation guidance and assistance for software development workflows.

Faster Whisper accelerates speech-to-text transcription using Whisper, providing quicker results for real-time or large audio files.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Helps with Azure, AI as part of deploying and managing cloud infrastructure workflows.

Helps with Azure, AI as part of deploying and managing cloud infrastructure workflows.

Optimize Deepgram transcription accuracy and efficiency through automated parameter adjustments and performance analysis.

Analyzes Deepgram transcription errors using bundled diagnostics to identify root causes and suggest improvements.

This skill leverages Deepgram to identify and flag frequent speech recognition errors, improving transcription accuracy and reducing manual correction needs.

Automates Deepgram API key installation and authentication for secure audio transcription workflows.

Convert YouTube videos to vertical short-form clips using yt-dlp, FFmpeg, and Whisper. Auto-detects highlights, crops to 9:16, and overlays subtitles.

Local speech-to-text using faster-whisper — 4-6x faster than OpenAI Whisper with identical accuracy. GPU acceleration, SRT/VTT/TTML subtitles, speaker diarization, and chapter detection.