mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit

This model was converted to MLX format from Aratako/Irodori-TTS-500M-v2-VoiceDesign using mlx-audio version 0.4.3.

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

The VoiceDesign variant generates speech conditioned on a text description of the desired voice instead of a reference audio clip.

Use with mlx-audio

pip install -U mlx-audio

CLI Example

python -m mlx_audio.tts.generate \
  --model mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit \
  --text "こんにちは、テストです。" \
  --instruct "穏やかで落ち着いた女性の声。ゆっくりと話す。"

Python Example

from mlx_audio.tts.generate import generate_audio

generate_audio(
    model="mlx-community/Irodori-TTS-500M-v2-VoiceDesign-4bit",
    text="こんにちは、テストです。",
    instruct="穏やかで落ち着いた女性の声。ゆっくりと話す。",
    file_prefix="output",
)