Cài đặt dots.tts bằng Conda

conda env create -f environment.yml
conda activate dots_tts

# sanity check
dots.tts --help

usage: dots.tts [-h] --model-name-or-path MODEL_NAME_OR_PATH [--revision REVISION] [--cache-dir CACHE_DIR] --text TEXT [--output OUTPUT] [--precision PRECISION] [--seed SEED] [--prompt-audio PROMPT_AUDIO]
                [--prompt-text PROMPT_TEXT] [--language LANGUAGE] [--template-name {tts,instruction_tts,text_to_audio,tts_interleave}] [--ode-method ODE_METHOD] [--num-steps NUM_STEPS]
                [--guidance-scale GUIDANCE_SCALE] [--speaker-scale SPEAKER_SCALE] [--max-generate-length MAX_GENERATE_LENGTH] [--max-sequence-length MAX_SEQUENCE_LENGTH] [--normalize-text]
                [--profile-inference] [--profile-inference-calls]

dots.tts inference CLI.

options:
  -h, --help            show this help message and exit
  --model-name-or-path MODEL_NAME_OR_PATH
                        Local pretrained directory or Hugging Face repo id
  --revision REVISION   Optional Hugging Face revision
  --cache-dir CACHE_DIR
                        Optional Hugging Face cache dir
  --text TEXT           Input text
  --output OUTPUT       Output wav file path
  --precision PRECISION
                        Inference precision
  --seed SEED           Random seed for inference.
  --prompt-audio PROMPT_AUDIO
                        Path to prompt audio
  --prompt-text PROMPT_TEXT
                        Transcript of prompt audio
  --language LANGUAGE   Language tag mode. Default: none. Supported values: none, auto_detect, or a language code/name such as EN/en/english/chinese.
  --template-name {tts,instruction_tts,text_to_audio,tts_interleave}
                        Named template preset for generation.
  --ode-method ODE_METHOD
                        ODE solver method (default: artifact setting, otherwise euler)
  --num-steps NUM_STEPS
                        Sampling steps (default: artifact setting, otherwise 10)
  --guidance-scale GUIDANCE_SCALE
                        Classifier-free guidance scale (default: artifact setting, otherwise 1.2)
  --speaker-scale SPEAKER_SCALE
                        Scale applied to the reference speaker embedding
  --max-generate-length MAX_GENERATE_LENGTH
                        Maximum total audio patch count (prompt + generated)
  --max-sequence-length MAX_SEQUENCE_LENGTH
                        Maximum LLM sequence length used for schedule validation and optimized StaticCache
  --normalize-text      Whether to normalize text before inference
  --profile-inference   Collect per-module inference timing statistics
  --profile-inference-calls
                        Log each profiled inference call timing

# Random-voice sampling (no reference) — only meaningful with a fine-tuned
# single-speaker checkpoint
dots.tts --model-name-or-path dots-studio/dots.tts-soar --precision float32 --text "Hello, this is a quick speech synthesis test." --output output.wav

curl -L -O "http://cva4.com/audio/prompt_english_female1.wav"

# X-vector-only voice cloning (reference audio only — timbre from speaker x-vector)
dots.tts --model-name-or-path dots-studio/dots.tts-soar --precision float32 --text "Hello, this is a zero-shot voice cloning demonstration." --prompt-audio prompt_english_female1.wav --output clone.wav

# Continuation voice cloning (reference audio + transcript) — recommended, best SIM
dots.tts --model-name-or-path dots-studio/dots.tts-soar --precision float32 --text "Hello, this is a zero-shot voice cloning demonstration." --prompt-audio prompt_english_female1.wav --prompt-text "In order to win, you must expect to win." --output clone.wav

from dots_tts.runtime import DotsTtsRuntime
import soundfile as sf

runtime = DotsTtsRuntime.from_pretrained(
    "dots-studio/dots.tts-soar",
    precision="float32",
    optimize=False,  # torch.compile acceleration (warmup at load, faster steady-state)
)

result = runtime.generate(
    text="Hello, this is a quick speech synthesis test.",
    prompt_audio_path="prompt_english_female1.wav",
    prompt_text="In order to win, you must expect to win.",
    num_steps=10,
    guidance_scale=1.2,
)

sf.write("clone.wav", result["audio"].float().cpu().squeeze().numpy(), result["sample_rate"])

python dots_test.py

git clone https://github.com/studio-dots-ai/dots.tts.git
cd dots.tts

python apps/gradio/app.py --model-name-or-path dots-studio/dots.tts-soar --precision float32