Alex 4989e0a7e8 Fix audio quality: use original orpheus_tts convert_to_audio decoder ...

Our custom SNAC redistribution had wrong layer mapping (positions
1,2 vs 1,4 for layer 2) and incorrect audio slicing. Switched to
importing convert_to_audio directly from orpheus_tts.decoder which
handles the sliding window, layer redistribution, and 2048:4096
audio slice correctly.

Audio now sounds clean with only a subtle boundary artifact on the
first token group (inherent to SNAC streaming, not our code).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-14 01:07:29 -05:00

23 KiB

Raw Blame History

View Raw