Python interface for Mary TTS
Project description
A pretty simple HTTP based interface to MaryTTS intended to make using this excellent TTS for waveform and IPA generation as convenient as possible.
Target audience are developers who would like to use MaryTTS as-is for speech synthesis in their Python application on GNU/Linux operating systems.
Constructive comments, patches and pull-requests are very welcome.
Examples
First, imports:
import wave import StringIO from marytts import MaryTTS
english (default) synthesis:
marytts = MaryTTS() wavs = marytts.synth_wav(‘Hello World!’) wav = wave.open(StringIO.StringIO(wavs)) print wav.getnchannels(), wav.getframerate(), wav.getnframes()
result:
1 16000 21520
try a different language:
marytts.locale = ‘de’ marytts.voice = ‘bits3’ wavs = marytts.synth_wav(‘Hallo Welt!’) wav = wave.open(StringIO.StringIO(wavs)) print wav.getnchannels(), wav.getframerate(), wav.getnframes()
result:
1 16000 16760
### List Available Voices
l = marytts.voices
result:
>>> l[0] ['upmc-pierre-hsmm', 'fr', 'male', 'hmm'] >>> l[1] ['dfki-pavoque-neutral-hsmm', 'de', 'male', 'hmm'] >>> l[2] ['cmu-slt-hsmm', 'en_US', 'female', 'hmm'] >>> l[3] ['cmu-rms-hsmm', 'en_US', 'male', 'hmm'] ...
### Grapheme to Phoneme (G2P) Conversion
marytts.locale = ‘en_US’ marytts.voice = ‘cmu-rms-hsmm’ cs = marytts.g2p (‘Hello World!’)
result:
>>> cs "h @ - ' l @U ' w r= l d"
### Synthesize Phonemes
wavs = marytts.synth_wav(“h @ - ‘ l @U ‘ w r= l d”, fmt=’xs’) wav = wave.open(StringIO.StringIO(wavs)) print wav.getnchannels(), wav.getframerate(), wav.getnframes()
result:
1 16000 21520
Links
<https://github.com/marytts/marytts> [MaryTTS on github]
Requirements
Python 2.7
MaryTTS server running
License
My own code is Apache-2.0 licensed unless otherwise noted in the script’s copyright headers.
