Downloads · 30 days
88
27% of all-time downloads
joeygambino/ltx23-accent-american-audio-lora
ltx23-accent-american-audio-lora is a text-to-video model from joeygambino. Use it when you need video from a text prompt. It is set up for diffusion-single-file. The card lists the license as other.
Makes accent wording in your prompt actually work. LTX-2.3's voice prior ignores accent requests in exactly the regions where you need them most — young female characters default to Australian-leaning voices even when…
Downloads · 30 days
88
27% of all-time downloads
All-time downloads
324
Public
Repo size
177 MB
Likes
2
Public
Click a slice to open those files.
.safetensors177 MB · 100%
From the Hugging Face model README
Makes accent wording in your prompt actually work. LTX-2.3's voice prior ignores accent requests in exactly the regions where you need them most — young female characters default to Australian-leaning voices even when the prompt says "in a casual American accent". This LoRA turns that wording into a reliable control.
This LoRA cannot help you at the wrong frame rate. LTX-2.3's joint audio-video prior is 24 fps-native, and render fps is a hidden accent dial: at 25 fps the same prompt and seed render non-rhotic southern British, at 30 fps broad Australian — and off-24 fps overrides accent wording entirely, LoRA or no LoRA. Set your workflow's fps/frame_rate to 24, then use this LoRA. (Dose-response verified by A/B on identical configs, 2026-07-30.)
A/B matrix on the hardest region (young pale-skinned woman, casual camcorder monologue), 24 fps, two seeds per cell, blind phonetic review:
| spoken-line wording | without LoRA | with LoRA @ 1.0 |
|---|---|---|
| no accent stated | Australian | Australian |
| "saying in a casual American accent" | Australian (both seeds) | General American (both seeds) |
| rich scaffold ("her voice is a low American voice with a slight rasp, speaking in a casual American accent") | Australian (both seeds) | General American |
The pattern: the LoRA does not force American unconditionally — it makes the model obey the accent you ask for in regions where the base model refuses. State the accent on every spoken line ("in a casual American accent"); the LoRA does the enforcing.
1,152 LoRA tensors, all of them in the audio branches — audio_attn1 (480),
audio_attn2 (480), audio_ff (192). Zero video tensors, zero cross-modal
(video_to_audio / audio_to_video) tensors. Video content, faces, and lip
motion are mathematically untouched.
LoRA weights follow the LTX-2 Community License of the base model. Training audio: LibriSpeech, CC BY 4.0.