py-marytts 0.1.3

Python interface for Mary TTS

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 LGPLv3 licensed unless otherwise noted in the script’s copyright headers.

Author

Guenter Bartsch <<[e-mail]>>