darknoon

Transcribe audio files using the Gemini API, with an optional custom prompt to change the output format or task. This skill is ideal for transcribing speech, diarizing audio, extracting meeting notes, summarizing recordings, or processing audio with specific instructions.

Transcribes audio files (m4a, mp3, wav, ogg, flac, aac, webm, mp4) to text using local whisper-cpp (offline, no API). Ideal for local transcription, offline speech-to-text conversion, or processing audio recordings without external data transfer. It converts files to 16kHz WAV via ffmpeg before running whisper-cli locally, but does not perform speaker diarization or advanced transcription.