CoolFace
Modelpublic

aufklarer/Qwen3-TTS-12Hz-0.6B-CustomVoice-MLX-4bit

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes136downloads
Model Card

Qwen3 TTS 12Hz 0.6B CustomVoice — MLX 4-bit

MLX 4-bit quantized conversion of Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice for Apple Silicon inference.

Usage

Used by speech-swift Qwen3TTS module:

swift
let model = try await Qwen3TTSModel.fromPretrained(
    modelId: TTSModelVariant.customVoice.rawValue
)
let audio = try model.synthesize("Hello!", speaker: "ryan")
bash
audio speak "Hello!" --model custom-voice --speaker ryan -o output.wav

Model Details

  • —Architecture: Qwen3-TTS (Talker transformer + Code Predictor + Mimi speech tokenizer decoder)
  • —Parameters: 0.6B
  • —Quantization: 4-bit (MLX, talker only)
  • —Size: ~964 MB
  • —Sample rate: 24 kHz
  • —Codec rate: 12.5 Hz
  • —Voices: 9 preset voices + instruction-based style control