PyPI page
Author:
Laurent-Philippe Albou
Summary:
Remote-compatible and local TTS/STT, streaming voice output, and optional voice cloning for AI applications
Latest version:
0.15.0
Required dependencies:
appdirs
|
numpy
|
requests
Optional dependencies:
accelerate
|
aec-audio-processing
|
audioread
|
av
|
black
|
einops
|
f5-tts
|
fastapi
|
faster-whisper
|
flake8
|
httpx
|
huggingface-hub
|
librosa
|
mkdocs
|
mkdocs-material
|
mlx-whisper
|
numpy
|
nvidia-cublas-cu12
|
nvidia-cuda-runtime-cu12
|
nvidia-cudnn-cu12
|
omnivoice
|
onnxruntime
|
pillow
|
piper-tts
|
pytest
|
python-multipart
|
safetensors
|
sentencepiece
|
sounddevice
|
soundfile
|
tomli
|
torch
|
torchaudio
|
torchvision
|
transformers
|
uvicorn
|
webrtcvad-wheels
Downloads last day:
279
Downloads last week:
494
Downloads last month:
3,716
7-day smoothing