
Decodes the bound audio clip and plays it out as a real-time stream of AudioFrame chunks, looping the playlist when asked. Use it for offline batch processing or deterministic, repeatable audio benchmarks.
Offline transcription — denoise the clip then transcribe and report as JSON.
Voice-activity evaluation over a fixed clip.
frame_size_ms sets each chunk's duration; the final chunk of a file is shorter when the length does not divide evenly. The emitted channel count matches the source layout with no downmix.sample_rate left at the sentinel keeps the file's native rate, while a positive value resamples on the fly; this is captured per opened file, whereas frame_size_ms, repeat, and the bound slot can be changed at runtime.repeat loops the playlist indefinitely when on, and stops after the last file when off.Automated release