tts
TLDR
Synthesize speech
$ tts --text "[Hello world]"
Save to file$ tts --text "[Hello]" --out_path [output.wav]
List models$ tts --list_models
Use specific model$ tts --text "[text]" --model_name [tts_models/en/ljspeech/tacotron2-DDC]
List speakers$ tts --model_name [model] --list_speakers
SYNOPSIS
tts [--text text] [--outpath file] [--modelname model] [options]
DESCRIPTION
tts synthesizes speech. It's Coqui TTS CLI.
Neural TTS. Deep learning synthesis.
Multiple models. Various voices.
Multi-speaker. Voice selection.
High quality. Natural sounding.
PARAMETERS
--text TEXT
Input text.--out_path FILE
Output audio file.--model_name MODEL
TTS model.--list_models
Show models.--speaker_idx ID
Speaker selection.
CAVEATS
Python required. Large model downloads. GPU recommended.
HISTORY
TTS (Coqui TTS) is an open-source deep learning text-to-speech toolkit with multiple models.
