mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 13:20:39 -07:00
Route MLX load, inference, unload, reset, cache cleanup, and shutdown through a single worker. Add affinity and concurrent-unload regression coverage.\n\nVerified: 17 related backend tests; frontend CI; cargo check.
34 lines
775 B
Python
34 lines
775 B
Python
"""
|
|
TTS inference module - delegates to backend abstraction layer.
|
|
"""
|
|
|
|
import io
|
|
|
|
import numpy as np
|
|
import soundfile as sf
|
|
|
|
from ..backends import TTSBackend, get_tts_backend, unload_backend
|
|
|
|
|
|
def get_tts_model() -> TTSBackend:
|
|
"""
|
|
Get TTS backend instance (MLX or PyTorch based on platform).
|
|
|
|
Returns:
|
|
TTS backend instance
|
|
"""
|
|
return get_tts_backend()
|
|
|
|
|
|
async def unload_tts_model():
|
|
"""Unload TTS model to free memory, serialized onto the MLX worker."""
|
|
await unload_backend(get_tts_backend())
|
|
|
|
|
|
def audio_to_wav_bytes(audio: np.ndarray, sample_rate: int) -> bytes:
|
|
"""Convert audio array to WAV bytes."""
|
|
buffer = io.BytesIO()
|
|
sf.write(buffer, audio, sample_rate, format="WAV")
|
|
buffer.seek(0)
|
|
return buffer.read()
|