eSpeak (a compact open source software speech synthesizer) eSpeak produces good quality English speech. It uses a different synthesis method from other open source text to speech (TTS) engines, and sounds quite different. It's perhaps not as natural or "smooth", but some find the articulation clearer and easier to listen to for long periods. It can run as a command line program to speak text from a file or from stdin. Build options (environment variables): PULSE Build PulseAudio output support (yes/no)? Default is "yes". PORTAUDIO Build PortAudio output support (yes/no/auto)? Default is "auto", which will build in PortAudio support if it's installed. Use PortAudio[1] for plain ALSA[2] audio output, if you don't want to use PulseAudio. However, if you're happy with PulseAudio, it's recommended NOT to build PortAudio support into espeak (you won't need it anyway). Note that if both options are "no" (or if PULSE=no and portaudio isn't autodetected), the resulting binary will not be able to make sound (it will only produce .wav files). The slack-desc will be updated to let you know which audio drivers (if any) were included. [1] Using PortAudio with espeak results in a lot of scary-looking warnings from espeak, but you can ignore them so long as you can hear its speech. [2] Or JACK audio, if your portaudio package was built with jack installed. Or... PortAudio can also feed audio to PulseAudio, if its daemon is running. Or, if you have OSS modules loaded, PortAudio can use that, too. The Linux audio driver ecosystem is a really weird place.