LongCat-AudioDiT-3.5B-bf16

mlx-community/LongCat-AudioDiT-3.5B-bf16

This model was converted to MLX format from meituan-longcat/LongCat-AudioDiT-3.5B using mlx-audio version 0.4.3.

Refer to the original model card for more details on the model.

Use with mlx-audio

pip install -U mlx-audio

Usage

from mlx_audio.tts.utils import load

model = load("mlx-community/LongCat-AudioDiT-3.5B-bf16")

result = next(model.generate("Hello, this is a test of AudioDiT."))
audio = result.audio  # mlx array, 24kHz

Play audio directly:

from mlx_audio.tts.audio_player import AudioPlayer

player = AudioPlayer(sample_rate=24000)
result = next(model.generate("The quick brown fox jumps over the lazy dog."))
player.queue_audio(result.audio)
player.wait_for_drain()
player.stop()

Voice Cloning

Clone any voice using a reference audio sample and its transcript. Use guidance_method="apg" for best voice cloning quality:

result = next(model.generate(
    text="Today is warm turning to rain, with good air quality.",
    ref_audio="reference.wav",
    ref_text="Transcript of the reference audio.",
    guidance_method="apg",
    cfg_strength=4.0,
    steps=16,
))

Zero-Shot Generation (Chinese)

result = next(model.generate(
    text="今天晴暖转阴雨，空气质量优至良，空气相对湿度较低。",
    steps=16,
    cfg_strength=4.0,
))

Generation Parameters

CLI

# Zero-shot TTS
python -m mlx_audio.tts.generate \
  --model mlx-community/LongCat-AudioDiT-3.5B-bf16 \
  --text "Hello, this is a test of AudioDiT." \
  --play

# Voice cloning
python -m mlx_audio.tts.generate \
  --model mlx-community/LongCat-AudioDiT-3.5B-bf16 \
  --text "Today is warm turning to rain." \
  --ref_audio reference.wav \
  --ref_text "Transcript of the reference audio." \
  --play

License

LongCat-AudioDiT weights and code are released under the MIT License.