mbrola(1) multilingual software speech synthesizer


mbrola [options]<voice_database><pho_file>...<output_file>


mbrola is a speech synthesizer based on the concatenation of diphones. It takes a list of phonemes as input, together with prosodic information (duration of phonemes and a piecewise linear description of pitch), and produces speech samples on 16 bits (linear), at the sampling frequency of the diphone database.

It is therefore NOT a Text-To-Speech (TTS) synthesizer, since it does not accept raw text as input. In order to obtain a full TTS system, you need to use this synthesizer in combination with a text processing system that produces phonetic and prosodic commands. For instance, you may use package freephone to obtain complete English TTS.

A `-' instead of pho_file or output_file means stdin or stdout. Extension of output_file ( raw, au, wav, aiff ) tells the wanted audio format.


mbrola understands following command line options.

Show summary of options.

Display the database information if any.

Ignore fatal errors on unknown diphone.
-c comment_char
Set COMMENT char (escape sequence in pho files).
-F flush_command
Set FLUSH command name.
-v volume
Volume ratio. Float ratio applied to output samples.
-f freq_ratio
Frequency ratio. Float ratio applied to pitch points.
-t time_ratio
Time ratio. Float ratio applied to phone durations.
-l voice_freq
Voice frequency. Target frequency for voice quality in Hz.
-R rename_list
Phoneme rename list of the form: `a A b B ...'
-C clone_list
Phoneme clone list of the form: `a A b B ...'
-I file
Initialization file containing one command per line. CLONE, RENAME, VOICE, TIME, FREQ, VOLUME, FLUSH, COMMENT, and IGNORE are available.


mbrola was written by Dr Thierry Dutoit <[email protected]>

This manual page was written by Igor B. Poretsky <[email protected]>, for the Debian project (but may be used by others).