Last updated 24 August 2026
Where the voice comes from
This uses the Web Speech API, built into modern browsers — the same underlying system your device already uses for accessibility features and voice assistants. No audio is generated on a server and sent back to you; your own device does the speaking, which is also why the exact voices available differ from one device to another.
The voices come from your device
Nothing here is generated on a server. The tool asks your browser to speak, and the browser uses voices already installed on your phone or computer. That is why it costs nothing and why your text never leaves the device — and also why the voice list is different for everyone.
Windows, macOS, Android and iOS all ship different sets, and browsers expose them differently. A voice you pick on your laptop may simply not exist on your phone. Some voices are downloaded on demand by the operating system, so the list can grow after you install extra language packs in your system settings.
Quality varies with it. The newer neural voices sound close to natural; older built-in ones are noticeably robotic. Long passages can also be cut short by the browser, so for anything lengthy it is worth splitting the text into sections rather than pasting it all at once.
Common questions
Where do the voices come from?
Your operating system and browser — not a server. Available voices vary by device; phones and computers each ship with their own set, which is why the list looks different depending on what you're using.
Is my text sent anywhere?
No. Speech synthesis happens locally using your browser's built-in engine. Nothing is uploaded or stored.
Can I download the audio?
Not with this tool — it plays directly through your device's speakers rather than producing a file. If you need an audio file, that requires a different kind of text-to-speech service.