LinuxCommandLibrary

flite

Convert text to speech

TLDR

List all available voices

$ flite -lv
copy

Convert a text string to speech
$ flite -t "[string]"
copy

Convert the contents of a file to speech
$ flite -f [path/to/file.txt]
copy

Use the specified voice
$ flite -voice [file://path/to/filename.flitevox|url]
copy

Store output into a wav file
$ flite -voice [file://path/to/filename.flitevox|url] -f [path/to/file.txt] -o [output.wav]
copy

Display version
$ flite --version
copy

SYNOPSIS

flite [options] [text_file]

PARAMETERS

-t text
    Synthesizes the given text string directly from the command line. This allows for quick testing without needing a separate text file.

-f file
    Synthesizes the text from the specified input file.

-o output_wav_file
    Specifies the output WAV file to store the synthesized speech. If not specified, the audio is typically played directly through the system's audio output.

-voice voice_name
    Selects the voice to use for synthesis. Available voices depend on the Flite installation. Common voices include 'kal', 'awb', and 'rms'.

-help
    Displays the help menu with the usage and available options.

-version
    Displays the flite version

DESCRIPTION

Flite (Festival Lite) is a small, fast run-time text-to-speech synthesis engine. It is designed for embedded systems and other resource-constrained environments where a full-blown TTS system like Festival might be too heavy. Flite supports a relatively small set of voices and languages compared to Festival, but its compact size and efficiency make it a good choice for applications where low latency and minimal resource usage are critical.
It allows users to convert text into speech using various available voices.
Flite is commonly used in applications like accessibility tools, embedded devices, and voice assistants where speech synthesis is required but resources are limited.

CAVEATS

Flite's voice quality is generally considered lower than more advanced TTS systems like Festival or commercial offerings. The selection of voices and languages is also more limited.
The performance and memory usage can still vary depending on the chosen voice and the complexity of the text being synthesized.

<I>VOICES</I>

The choice of voice significantly impacts the output quality and characteristics of the synthesized speech. Experiment with different available voices to find the one best suited for your specific application. You can usually find the available voices in /usr/share/flite/voices

HISTORY

Flite was developed as a lightweight alternative to the Festival speech synthesis system. It aimed to provide a smaller footprint and faster execution speed, making it suitable for embedded devices and other resource-constrained environments. Its development was driven by the need for TTS capabilities in applications where Festival was too resource-intensive. It has been widely used in various projects requiring speech synthesis, particularly where portability and low resource usage are important.

SEE ALSO

festival(1)

Copied to clipboard