EXTENSIONS

Transcribe audio files using mlx_whisper on Apple Silicon. Runs the mlx_whisper CLI, captures the JSON output, and stores the full transcript (segments + language) as a swamp resource for downstream pipeline steps. Requires mlx_whisper installed (pip install mlx-whisper).

Manage Voicebox TTS voice profiles, load TTS engines, generate speech audio, and inspect server health via the Voicebox HTTP API.