PyPI page
Author:
Fluxions AI
Summary:
Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU. Ships with a full real-time voice assistant (WebRTC, ASR, local LLM, OpenAI Realtime API compatible).
Latest version:
1.2.3
Required dependencies:
einops
|
httpx
|
huggingface-hub
|
julius
|
mlx
|
numpy
|
pydantic
|
safetensors
|
soundfile
|
tiktoken
|
tokenizers
|
torch
|
torchaudio
|
torchcodec
|
transformers
Optional dependencies:
aiohttp
|
aiortc
|
av
|
claude-agent-sdk
|
faster-whisper
|
filelock
|
flash-attn
|
gradio
|
mlx
|
mlx-whisper
|
moonshine-voice
|
nvidia-cublas-cu12
|
onnxruntime
|
openai-whisper
Downloads last day:
3
Downloads last week:
118
Downloads last month:
908
7-day smoothing