| --- |
| base_model: LunaFox/DraculaFlow-TTS |
| language: |
| - en |
| library_name: mlx |
| license: apache-2.0 |
| pipeline_tag: text-to-speech |
| tags: |
| - mlx |
| - text-to-speech |
| - audio |
| - tts |
| --- |
| |
| # DraculaFlow-TTS-mlx |
|
|
| This repository contains the MLX-converted weights for **DraculaFlow-TTS**, optimized for fast inference on Apple Silicon using [mlx-audio](https://github.com/Blaizzy/mlx-audio). |
|
|
| * **Original Hugging Face Model**: [LunaFox/DraculaFlow-TTS](https://huggingface.co/LunaFox/DraculaFlow-TTS) |
|
|
| --- |
|
|
| ## Installation |
|
|
| Install `mlx-audio`: |
|
|
| ```bash |
| pip install mlx-audio |
| ``` |
|
|
| --- |
|
|
| ## Usage |
|
|
| ### 1. Command Line Interface (CLI) |
|
|
| Generate audio clips directly from the terminal using `mlx_audio.tts.generate`: |
|
|
| ```bash |
| python -m mlx_audio.tts.generate \ |
| --model LunaFox/DraculaFlow-TTS-mlx \ |
| --text "We are smoking joint out of a custom carved bong." \ |
| --voice dracula_flow \ |
| --output_path ./output.wav |
| ``` |
|
|
| To play the audio immediately upon generation, add the `--play` flag: |
|
|
| ```bash |
| python -m mlx_audio.tts.generate \ |
| --model LunaFox/DraculaFlow-TTS-mlx \ |
| --text "This shit ain't nothing to me man." \ |
| --voice dracula_flow \ |
| --play |
| ``` |
|
|
| ### 2. Python API |
|
|
| You can also generate audio clips within a Python script: |
|
|
| ```python |
| from mlx_audio.tts.generate import generate_audio |
| |
| generate_audio( |
| text="We are smoking joint out of a custom carved bong.", |
| model="LunaFox/DraculaFlow-TTS-mlx", |
| voice="dracula_flow", |
| output_path="./output.wav", |
| ) |
| ``` |
|
|
| --- |
|
|
| ## Details |
|
|
| * **Architecture**: Qwen3 TTS (`qwen3_tts`) |
| * **Speaker Voice ID**: `dracula_flow` |
| * **Framework**: [MLX](https://github.com/ml-explore/mlx) / [mlx-audio](https://github.com/Blaizzy/mlx-audio) |
|
|
