mirror of
https://github.com/justLV/onju-v2
synced 2026-04-21 15:47:55 +00:00
13f9d59245
Adds mlx-audio-based Qwen3-TTS as an alternative to ElevenLabs, enabling fully offline voice synthesis with voice cloning from a short reference audio clip. Benchmarked at 0.52x RTF (sub-realtime) on Apple Silicon with the 1.7B-Base-4bit model.
11 lines
94 B
Text
11 lines
94 B
Text
httpx
|
|
mlx-audio>=0.3.1
|
|
numpy
|
|
onnxruntime
|
|
openai
|
|
opuslib
|
|
pyaudio
|
|
pydub
|
|
PyYAML
|
|
scipy
|
|
silero-vad
|