PyPI page
Home page
Author:
Kolja Beigel
License:
MIT
Summary:
Stream text into audio with an easy-to-use, highly configurable library delivering voice output with minimal latency.
Latest version:
0.8.10
Required dependencies:
audioop-lts
|
pydub
|
resampy
|
stream2sentence
Optional dependencies:
audioop-lts
|
azure-cognitiveservices-speech
|
camb-sdk
|
cartesia
|
chatterbox-tts
|
cn2an
|
coqui-tts
|
cutlet
|
edge-tts
|
elevenlabs
|
espeakng-loader
|
fastapi
|
fasttext-predict
|
fugashi
|
gtts
|
hangul-romanize
|
huggingface-hub
|
inflect
|
jaconv
|
jieba
|
kokoro
|
lhotse
|
librosa
|
mecab-python3
|
mojimoji
|
munch
|
neutts
|
nltk
|
num2words
|
numba
|
numpy
|
omnilingual-asr
|
omnivoice
|
onnxruntime
|
openai
|
ordered-set
|
phonemizer
|
piper-phonemize
|
pocket-tts
|
pyaudio
|
pydub
|
pyopenjtalk
|
pypinyin
|
pyttsx3
|
pyyaml
|
realtimetts-qwen-native
|
realtimetts-qwen-native-cpu
|
requests
|
resampy
|
safetensors
|
scipy
|
setuptools
|
silero-vad
|
snac
|
soprano-tts
|
sopro
|
soundfile
|
stream2sentence
|
tensorboard
|
torch
|
torchaudio
|
transformers
|
typecast-python
|
unidecode
|
unidic-lite
|
uvicorn
|
vocos
Downloads last day:
94
Downloads last week:
641
Downloads last month:
2,531
7-day smoothing