Free text to speech. No sign-up.
Paste text, import a file, and download natural-sounding audio. Use several voices in one script and switch voices while it plays. It all runs on your device, so your text is never uploaded.
Daily tokens … left (1 token = 1 word)
Part of
Script tags and pronunciation
Several voices: start a line with a voice name in brackets, like [Heart]: Hello! then [George]: Hi there. The voice stays until you change it. [default] goes back to the voice picked above.
Silence: add [pause] or [pause 2s] (up to 5 seconds).
Pronunciation: one rule per line, as word = how it should sound.
Links, emojis and markdown symbols are skipped automatically.
Live: change voice, speed or pause while it plays.
Voice engine: starts loading when you begin typing (about 80 MB, first visit only).
Your audio
Audio is created by AI. You are responsible for the text you convert and how you use the audio.