pip install git+https://github.com/HumeAI/tada.git

pip install -e .

import torch
import torchaudio

from tada.modules.encoder import Encoder, EncoderOutput
from tada.modules.tada import TadaForCausalLM

device = "cuda"

# Encoder is loaded separately (not inside the model)
encoder = Encoder.from_pretrained("HumeAI/tada-codec", subfolder="encoder").to(device)
model = TadaForCausalLM.from_pretrained("HumeAI/tada-3b-ml", torch_dtype=torch.bfloat16).to(device)

audio, sample_rate = torchaudio.load("samples/ljspeech.wav")
audio = audio.to(device)
prompt_text = "The examination and testimony of the experts, enabled the commission to conclude that five shots may have been fired."
prompt = encoder(
    audio, text=[prompt_text], sample_rate=sample_rate
)

# Optional: save prompt to skip encoder on future runs
# prompt.save("prompt_cache.pt")
# prompt = EncoderOutput.load("prompt_cache.pt", device=device)

output = model.generate(
    prompt=prompt,
    text="Please call Stella. Ask her to bring these things with her from the store.",
)

import torch
import torchaudio

from tada.modules.encoder import Encoder
from tada.modules.tada import TadaForCausalLM

device = "cuda"
encoder = Encoder.from_pretrained("HumeAI/tada-codec", subfolder="encoder", language="ja").to(device)
model = TadaForCausalLM.from_pretrained("HumeAI/tada-3b-ml", torch_dtype=torch.bfloat16).to(device)

# Load a reference audio clip in the target language
audio, sample_rate = torchaudio.load("samples/ja_prompt.wav")
audio = audio.to(device)

# For non-English prompts, provide the transcript so the encoder uses forced alignment
# instead of the built-in ASR (which is English-only)
prompt_text = "このムキムキのお兄さんがいるし バーだし少し高そうだと思いますよねこのバーの料金設定は良心的でした まあそんなに高くなかったです"
prompt = encoder(audio, text=[prompt_text], sample_rate=sample_rate)

output = model.generate(
    prompt=prompt,
    text="今日はとても良い天気ですね。散歩に行きましょう。",
)

prompt.print_alignment(model.tokenizer)

34 tokens | 10.50s audio
······The··exam····ination··and·····test···imony··of···the

output = model.generate(
    prompt=prompt,
    num_extra_steps=50
)

@article{dang2026tada,
  title={TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment},
  author={Dang, Trung and Rao, Sharath and Gupta, Ananya and Gagne, Christopher and Tzirakis, Panagiotis and Baird, Alice and Cłapa, Jakub Piotr and Chin, Peter and Cowen, Alan},
  journal={arXiv preprint arXiv:2602.23068},
  year={2026}
}