mARTin-B78 602cf9e5df feat: deterministic per-voice RNG seed for consistent voice across requests (v6.7) ... Each API request now seeds PyTorch's CPU and CUDA RNGs before generation. The seed is auto-derived from the voice name (stable MD5 hash) if not set in voices.json, so all existing voices get consistent voice character with zero config changes. Override per-voice with "seed": <int> in voices.json. Previously the sampling RNG was unseeded, causing pitch/modulation drift across requests even when speaker embeddings (.pt files) were identical. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>		2026-06-21 14:32:58 +02:00
..
openai_server.patch	feat: deterministic per-voice RNG seed for consistent voice across requests (v6.7)	2026-06-21 14:32:58 +02:00