Natural-sounding narration has to come from somewhere. What's worth knowing is where the generation actually happens, because that decides whether your book's text ever leaves your device.
Open PhonoLeaf Free 7-day trial · Sign in with Google · Nothing to installThe common approach is straightforward: the app sends the text of a page to a remote server, a neural voice model running there converts it to audio, and the resulting sound is streamed back to your device. It's a reasonable way to get a good-sounding voice without heavy processing on your phone, and it's how most consumer text-to-speech products work. The tradeoff is that your book's text passes through a server you don't control on its way to becoming sound, every single sentence.
PhonoLeaf's natural voice is generated by a neural model that runs directly on your device, not on a server. The text of your book never has to be sent anywhere to become audio. No backend of ours ever sees your books: your library list comes straight from Google Drive, and the reading itself happens entirely between your device and the book file.
Once a voice is downloaded and a book is saved for offline listening, yes: both speech generation and playback work with no connection at all.
PhonoLeaf uses published, open neural voice models, not a model trained on your own reading. They're downloaded once and run entirely on your device from then on.
No reading-content tracking. Voice generation happens on your device, so the text of a book never leaves it and there is no reading history on our side to analyse. The only thing the app downloads from us is the voice file itself, which is identical for every reader.
It's read-only, and you can revoke it at any time from your Google account settings or by signing out in the app, which also revokes the grant.
Read more about offline, private text to speech or see the full Privacy Policy.