Does text leave my computer?
Not when you use a local speech model. Synthesis runs on your machine.
Text to speech
Turn text into speech on your own computer
Paste text, choose a voice and listen. Playback starts while the rest is still being generated.
Direct answer
EdgeSpeak synthesizes speech locally with streaming output, a voice library you can extend, and WAV export, from the app, CLI or gateway.
Streaming playback
Speech starts as soon as the first audio is generated, so long text does not make you wait for the end.
Voices you can add
List compatible voices, then add or delete your own reusable voices.
Files and streams
Generate a WAV file or receive speech events from the local gateway.
edgespeak-cli speech --help
Use it in chat
The same voice reads replies aloud in voice chat.
FAQ
What output formats are available?
WAV files, or streaming speech events from the local gateway.
Can I add my own voice?
Yes. Voices are managed through the voices commands and API.