PyPI page
Home page
Author:
None
Summary:
Remote-compatible and local TTS/STT, streaming voice output, and optional voice cloning for AI applications
Latest version:
0.9.0
Required dependencies:
accelerate
|
aec-audio-processing
|
appdirs
|
audioread
|
av
|
f5-tts
|
huggingface_hub
|
librosa
|
numpy
|
omnivoice
|
pillow
|
requests
|
safetensors
|
soundfile
|
tomli
|
torch
|
torchaudio
|
torchvision
|
transformers
Optional dependencies:
black
|
einops
|
fastapi
|
faster-whisper
|
flake8
|
httpx
|
huggingface_hub
|
librosa
|
mkdocs
|
mkdocs-material
|
openai-whisper
|
piper-tts
|
pytest
|
python-multipart
|
safetensors
|
sentencepiece
|
sounddevice
|
soundfile
|
tiktoken
|
torch
|
uvicorn
|
webrtcvad
Downloads last day:
190
Downloads last week:
679
Downloads last month:
923