<h3 id="ltx-2.3-whisper-and-soft-spoken-audio-lora">LTX-2.3 Whisper &amp; Soft-Spoken Audio LoRA</h3>Base model: LTX-2.3 · Type: Audio-style LoRA · Rank: 32---## What this doesLTX-2.3 can generate dialogue, multi-speaker scenes, and full dynamic range audio including screaming — but it cannot whisper. This LoRA adds two quiet vocal registers to the model:- Whispering — devoiced, breathy, close-mic delivery- Soft-spoken — voiced but low-volume, intimate, relaxedThe LoRA targets only the three attention modules that write to the audio branch <code>audio_attn1</code>, <code>audio_attn2</code>, <code>video_to_audio_attn</code>). Video output is provably unchanged — no visual fighting, no style drift.---## UsageLoad at strength 1.0. The register is controlled entirely by the manner keyword in your prompt — no special strength tuning needed.### Trigger words (none, use natural language)| Whispering | <code>(woman, whispering)</code> | <code>(man, whispering quietly)</code> || Soft-spoken | <code>(woman, speaking softly)</code> | <code>(man, speaking softly)</code> |&gt; Note: Male whisper may requires the extra word <code>quietly</code> to tip the model over. <code>(man, whispering)</code> alone produces soft-spoken, not true whisper.### Prompt formatFollow the LTX-2.3 dialogue caption style:```a [scene description], ([gender], [manner]): "[what they say]", intimate ASMR```Examples:```a woman sitting close to a microphone in warm dim lighting, (woman, whispering): "close your eyes and listen"a man at a desk late at night, (man, speaking softly): "I've been thinking about this all day"a woman doing a skincare routine, (woman, whispering quietly): "this is my favourite step"```### Without manner keywordsUsing the LoRA without any manner keyword defaults to soft-spoken — a subtle volume-softening effect on whatever the base model would have generated. Useful as a gentle "quieter audio" modifier.---## What it can't do- No intra-clip register mixing. You can't have one character whisper and another speak normally in the same clip. The register applies to the whole generation. For mixed-register dialogue, generate each part separately and cut them together.- No magic above the vocoder ceiling. The audio chain passes through a mel spectrogram bottleneck. Breathy whisper HF energy gets partially smoothed. Expect intimate and quiet, not studio-crisp ASMR.- Video is untouched by design. If you want the visuals to also feel ASMR (soft lighting, close-up framing), describe that in the scene prompt — the LoRA won't help or hurt.---## Training details| | ||---|---|| Base model | LTX-2.3 dev || Steps | 2000 || Rank / Alpha | 32 / 32 || Target modules | audio_attn1, audio_attn2, video_to_audio_attn || Training resolution | 192×192, 97 frames (~4s @ 24fps) || Dataset | 74 clips, 8 voices (4F / 4M), 2 registers each |Clips were 4-second segments sourced from ASMR content across 8 speakers — 4 female (2 soft-spoken, 2 whisper) and 4 male (2 soft-spoken, 2 whisper). Captions used Whisper ASR transcription in <code>(gender, manner): "transcript", intimate ASMR</code> format.

LTX-2.3 Whisper & Soft-Spoken Audio LoRA

78 audio clips spanning 8 voices, both male and female, supporting whispering and softly spoken audio.

Files with SHA256: dbbdc78b8b6ef0405fe237b21ed6bb61eee0621665c267ea890ebb7784d5ceca