Generate your own prompts

If you want your XiVO to speak in your language that is not supported by XiVO, and you don’t want to record the whole package of sounds in a studio, you may generate them yourself with some text-to-speech services.

The following procedure will generate prompts for pt_BR (portuguese from Brazil) based on the Google TTS service.


There are two sets of prompts: the Asterisk prompts and the XiVO prompts. This procedure only covers the XiVO prompts, but it may be adapted for Asterisk prompts.

  1. Create an account on Transifex and join the team of translation of XiVO.

  2. Translate the prompts in the xivo-prompts resource.

  3. Go to and download the file on your XiVO. You should have a file named like for_use_xivo_xivo-prompt_pt_BR.ini.

  4. On your XiVO, download the tool to automate the use of Google TTS:

    chmod +x
  5. Then run the tool, and generate the sound files (set LANGUAGE and COUNTRY to your own language):

    mkdir -p wav/{digits,letters}
    cat for_use_xivo_xivo-prompt_${LANGUAGE}_${COUNTRY}.ini | while IFS='=' read file text ; do
      echo $file
      ./ -t "$text" -l ${LANGUAGE}-${COUNTRY} -s 1.4 -r 8000 -o wav/$file.wav
  6. Install the prompts on your system:

    mv wav /usr/share/asterisk/sounds/${LANGUAGE}_${COUNTRY}
  7. Make your language available in the web interface:

    sed -i "s/'nl_NL'/\0, '${LANGUAGE}_${COUNTRY}'/" /usr/share/xivo-web-interface/lib/
    systemctl restart spawn-fcgi

Note that this last modification may be erased after running xivo-upgrade.

And that’s it, you can configure a user to use your new language and he will hear the prompts in your language. You may also want to use the xivo-confd HTTP API to mass-update your users.