festival

general-purpose speech synthesis system

TLDR

Speak text

$ echo "[Hello world]" | festival --tts

Speak file contents

$ festival --tts [file.txt]

Start interactive mode

$ festival

Speak with specific voice

$ echo "[text]" | festival --tts --voice [voice_name]

Save speech to WAV

$ echo "[Hello]" | text2wave -o [output.wav]

List available voices

$ festival -b "(voice.list)"

festival is a general-purpose speech synthesis system. It converts text to speech using various synthesis techniques and can be controlled interactively or through scripts.The system supports multiple languages and voices, and can be extended with new voices. It's used for accessibility, voice interfaces, and audio content generation.

PARAMETERS

--tts

Text-to-speech mode (read from stdin).

-b expression

Evaluate Scheme expression.

-i

Interactive mode.

--voice name

Select voice.

--otype type

Output type (riff, aiff, etc.).

--server

Run as server.

--heap size

Heap size in bytes.

--help

Display help.

RELATED COMMANDS

text2wave: Convert text to audio filefestival_client: Connect to server

INSTALL

sudo apt install festival

sudo dnf install festival

sudo pacman -S festival

sudo zypper install festival

CAVEATS

Voice quality varies. Large texts may be slow. Some voices require additional downloads. Scheme knowledge helpful for customization.

HISTORY

Festival was developed at the Centre for Speech Technology Research at the University of Edinburgh by Alan Black and Paul Taylor starting in the 1990s. It became a widely-used open source TTS system.

RESOURCES

Homepage