26 lines (14 loc) · 597 Bytes

CHANGELOG

Version 0.4.0 (2026-01-14)

feat: add support for STT orchestration

Version 0.3.0 (2025-10-10)

feat: add support for passing audio as a {"audio": str | Path} mapping
feat: add support for passing audio as a {"waveform": np.ndarray | torch.tensor, "sample_rate": int} mapping

Version 0.2.1 (2025-09-20)

fix: fix "missing token" error message

Version 0.2.0 (2025-09-09)

Add support for Precision-2 model

Version 0.1.1 (2025-06-04)

Allow arbitrary kwargs in diarize, identify and voiceprint

Version 0.1.0 (2025-03-14)

Hello world!