Model reference · open weights

Dramabox

Audio ResembleAI Text→speech 1 build Its own licence terms 242 dl/mo

Dramabox is an open-weight audio or speech model from ResembleAI. Dramabox (BF16) weighs 8.5 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • Dramabox is a text-to-speech model developed by ResembleAI that uses prompts to control speaker identity, emotion, and vocal delivery.
  • It is an IC-LoRA fine-tune of the LTX-2.3 3.3B audio-only model, which is conditioned on Gemma 3 12B text embeddings.
  • The model supports English, requires approximately 24 GB of VRAM, and is distributed under the LTX-2 Community License.

Summary of the ResembleAI/Dramabox model card, 2026-10-01

What it is

Released byResembleAI
Released2026-04-17
VRAM8.5 GB for the weights

What it runs on

Memory and cards for Dramabox (BF16)

8.5 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBtight11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What ResembleAI says about Dramabox

Read the model card

Built on LTX-2 by Lightricks. Dramabox is Resemble AI's expressive TTS, trained on top of the LTX-2.3 audio branch under the LTX-2 Community License. Huge thanks to the Lightricks team for open-sourcing the base.

Made with ♥️ by

Dramabox is a prompt-driven TTS where the prompt itself controls everything — speaker identity, emotion, delivery, laughs, sighs, breaths, pauses, transitions. An optional 10-second voice reference clones the target timbre. It is an IC-LoRA fine-tune of the LTX-2.3 3.3B audio-only model (Diffusion Transformer + flow matching), conditioned on Gemma 3 12B text embeddings.

🤗 ModelResembleAI/Dramabox
🎭 Demo SpaceResembleAI/Dramabox (ZeroGPU)
💻 Coderesemble-ai/DramaBox
🏗️ Base modelLightricks/LTX-2.3
📜 LicenseLTX-2 Community License — see LICENSE

Quick start

Python (warm server — recommended, ~2.5 s / generation)

from src.inference_server import TTSServer

server = TTSServer(device="cuda")              # downloads weights on first run

server.generate_to_file(
    prompt='A woman speaks warmly, "Hello, how are you today?" '
           'She laughs, "Hahaha, it is so good to see you!"',
    output="output.wav",
    voice_ref="reference.wav",                  # optional, 10+ seconds of target voice
    cfg_scale=2.5,
    stg_scale=1.5,
    duration_multiplier=1.1,
    seed=42,
)

CLI

python src/inference.py \
    --prompt 'A woman speaks warmly, "Hello, how are you today?"' \
    --voice-sample reference.wav \
    --output output.wav \
    --cfg-scale 2.5 --stg-scale 1.5

Inference parameters

ParameterDefaultWhat it does
prompt—The scene description. Dialogue inside "double quotes", stage directions outside. See "Prompt format" below.
voice_ref (--voice-sample)NoneOptional 10+ s audio clip whose timbre the model clones. Without it, the model picks a voice that fits the description.
cfg_scale2.5Classifier-free guidance — how strictly the output follows the prompt. Lower = more natural, higher = more text-faithful but more dramatic. Auto-rescaled internally to prevent clipping at high cfg (see Auto rescale below).
stg_scale1.5Skip-token guidance — applied through the perturbed transformer block path (block 29). Increases expressive emphasis without saturating like cfg.
duration_multiplier (--duration-multiplier)1.1Multiplier on the auto-estimated speech length (10 % breathing-room headroom). Only used when gen_duration (or --gen-duration) is 0.
gen_duration (--gen-duration, "Target duration" slider)0 (auto)Explicit output duration in seconds. Set to 20–60 s for music or long scenes. Overrides the prompt-based estimate when > 0.
ref_duration (--ref-duration, "Reference duration" slider)10.0How many seconds of the voice reference the model conditions on (3–30 s). Longer ref → richer timbre capture, shorter ref → faster encode.
seed42Reproducibility.
rescale_scale (--rescale-scale)"auto"Latent-side CFG std-rescale. The default is a cfg-aware schedule (0 below cfg=2, ramping to 1.0 by cfg=10) that keeps the output peak below 0 dBFS at every cfg. Pass any float in [0, 1] to override or 0 to disable.
watermark (--no-watermark to disable)TrueApply Resemble Perth imperceptible neural watermark to the output. Survives MP3/AAC, common edits; ≈ 100 % detection accuracy.

Prompt format

Inside double quotes — the model speaks these literally:

  • Dialogue: "Hello, how are you?"
  • Phonetic vocalisations (one word, no separators): "Hahaha", "Hehehe", "Mmmmm", "Ugh", "Argh", "Hmm"

Outside quotes — stage directions interpreted as performance cues, never spoken:

  • She sighs deeply. · He clears his throat. · A long pause. · Her voice cracks. · He gulps nervously.

Avoid inside quotes (the model will speak the word literally): Sigh, Gasp, Cough, Ahem, Pfft.

Sample outputs

Regal Queen — Cold Fury to Venomous Whisper

A regal woman speaks with cold fury in a measured, low voice. She sighs deeply, "I have told you a thousand times, and yet here we are again." Her voice sharpens with rising anger, "Do you honestly think I enjoy repeating myself?! Do you?!" She lets out a cold, mocking laugh, "Hahaha, how utterly pathetic you are." She drops to a venomous whisper, leaning close, "Now get out of my sight before I do something we will both regret."

Reference

Generated

Catgirl — Uncontrollable Giggling

A playful girl speaks in a bright, singsong voice, already mid-giggle, "Hehehe, oh my gosh you should see your face right now, it is priceless!" She gasps for air between giggles, "Oh my, hehe, oh my, I cannot stop laughing!" She tries to compose herself with a long sigh, "Ahhhhh okay okay okay, I will stop, I promise I will stop." She leans in and whispers conspiratorially, "But seriously though, between you and me," then immediately loses it again, "Haha, no I, hehehe, I just cannot! You are way too funny, haha!" She snorts mid-laugh, "Pfft, oh no no no, that was so embarrassing, pretend you did not hear that!"

Reference

Generated

Villain — Sinister Laugh

A deep-voiced villain speaks with theatrical menace, chuckling softly at first, "Heh heh heh, ha ha ha ha ha! Oh, forgive me, forgive me." He catches his breath with a sinister grin, He clears his throat. "It is just SO amusing when they struggle, is it not?" His voice drips with contempt, "I ex

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms