chicogong

Offline speech-to-text and speaker diarization with the ffvoice engine. Use when the user wants to transcribe an audio file, generate subtitles (SRT/VTT/JSON), identify who spoke when (speaker diarization), caption or transcribe live microphone input, or list audio input devices — all fully on-device, with no cloud API and no API key.

Use when organizing, deduplicating, importing, auditing, repairing, or reporting on macOS photo and video collections, including folders, Photos.app libraries, external drives, Android imports, iCloud placeholders, EXIF or GPS metadata, Live Photos, corrupted media, quality scoring, 整理照片, 照片去重, 整理相册, 修复照片日期, 写真整理, or 사진 정리.