RHVoice is a free and open-source speech synthesizer.

RHVoice uses statistical parametric synthesis. It relies on existing
open-source speech technologies (mainly HTS and related software).

Voices are built from recordings of natural speech. They have small
footprints, because only statistical models are stored on users'
computers. And though the voices lack the naturalness of the
synthesizers which generate speech by combining segments of the
recordings themselves, they are still very intelligible and resemble
the speakers who recorded the source material.

Supported languages
Initially, RHVoice could speak only Russian. Now it also supports:

American and Scottish English
Brazilian Portuguese
Esperanto
Georgian
Ukrainian
Kyrgyz
Tatar
Macedonian
Albanian
Polish

RHVoice can be used via speech-dispatcher.