Skip to main content

Python script that lets you easily convert text to synthesized audio files, with help of Amazon's IVONA.

Project description

Build status Test coverage PyPI version Python versions License

Python script that lets you easily convert passed text to synthesized audio files, with help of Amazon’s IVONA. All you need is a pair of keys and this script. Yes, that’s literally everything you need to never speak again. If that’s your thing of course.

If you want to use IVONA Speech Cloud directly inside your Python project then you should have a look at python-ivona-api, which this script uses in the background.


>From PyPI (recommended):

$ pip install ivona_speak

With git clone:

$ git clone
$ pip install -r ivona-speak/requirements.txt
$ cd ivona-speak/bin


$ ivona-speak --help

  Easily convert passed text to synthesized audio files, with help of
  Amazon's IVONA. All you need is a pair of auth keys.

  See for more info.

  --help  Show this message and exit.

  synthesize*  Synthesize passed text and save it as an...
  list-voices  List available Ivona voices


You can provide keys either explicitly:

$ ivona-speak --access-key 'YOUR_ACTUAL_ACCESS_KEY' --secret-key 'YOUR_ACTUAL_SECRET_KEY' list-voices

or export them as environment variables:

$ export IVONA_ACCESS_KEY='...'
$ export IVONA_SECRET_KEY='...'
$ ivona-speak list-voices

The default subcommand is synthesize, so these do the same:

$ ivona-speak synthesize -o hello_world.mp3 'Hello world!'
$ ivona-speak -o hello_world.mp3 'Hello world!'

I want someone to say ‘Hello world!’, and say it quick:

$ ivona-speak synthesize -o hello_world.mp3 'Hello world!'

She sounds so nice. I want someone special to respond her:

$ ivona-speak synthesize -o response.mp3 -n Joey 'How you doin?'


Package was tested with the help of py.test and tox on Python 2.7, 3.4, 3.5 and 3.6 (see tox.ini).

Code coverage is available at Coveralls.

To run tests yourself you need to set environment variables with secret and access keys before running tox inside the repository:

$ pip install tox
$ export IVONA_ACCESS_KEY='..'
$ export IVONA_SECRET_KEY='..'
$ tox


Package source code is available at GitHub.

Feel free to use, ask, fork, star, report bugs, fix them, suggest enhancements, add functionality and point out any mistakes. Thanks!


Developed and maintained by Pythonity, a group of Python enthusiasts who love open source, have a neat blog and are available for hire.

Written by Paweł Adamczak.

Released under MIT License.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ivona_speak-0.3.0.tar.gz (7.2 kB view hashes)

Uploaded source

Built Distribution

ivona_speak-0.3.0-py2.py3-none-any.whl (8.6 kB view hashes)

Uploaded py2 py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page