From f14b80f6b42a0d0891718eb6284336b1694795cf Mon Sep 17 00:00:00 2001 From: historia Date: Wed, 2 Sep 2026 18:20:14 -0400 Subject: fix: ZONOS2 only generating 1024 tokens max --- app/docs/backend-sglomni.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'app/docs') diff --git a/app/docs/backend-sglomni.md b/app/docs/backend-sglomni.md index 13c8876..2aac93e 100644 --- a/app/docs/backend-sglomni.md +++ b/app/docs/backend-sglomni.md @@ -66,7 +66,7 @@ inside the start timeout. | `voxtral_tts` | Voxtral TTS 4B | preset named voices | e.g. `default`, `casual_male` | | `dots_tts_mf` | dots.tts (MeanFlow) | clone (reference required) | | | `fish_s2_pro` | Fish Speech S2-Pro | default voice or clone | needs ~24 GB VRAM (known OOM on a single RTX 3090, upstream issue #359) | -| `zonos2` | ZONOS2 | clone (reference required) | 44.1 kHz; FP8 pipeline falls back to bf16 on GPUs below compute capability 8.9 | +| `zonos2` | ZONOS2 | clone (reference required) | 44.1 kHz; FP8 pipeline falls back to bf16 on GPUs below compute capability 8.9; requests carry `max_new_tokens=12288` because the engine's 1024-frame default caps one request at ~12 s of speech | In the hub's **Generate Audiobooks** form the Model picker reads as a table, like the audio.cpp one: each entry's label is padded to the widest one and its -- cgit v1.2.3