Enter the script
Type text or import a plain-text file. A single generation can contain up to 4,000 characters.
System TTS · iPhone + iPad
Turn text into audio with Apple system voices.
Type or import up to 4,000 characters, choose a Chinese, English, or Japanese system voice, and adjust the reading rate and pitch. ClipFlow creates an audio result you can save or add to a video.
Readable text, reusable sound
How to convert text to speech on iPhone.
System TTS uses Apple's speech synthesizer rather than ClipFlow's online AI voice service.
Shape the delivery
Select a Chinese, English, or Japanese system voice, set rate from 10% to 100%, and set pitch from 0.5× to 2×.
Generate the audio
Create the speech result, then save it, trim it, change its speed, or use Add to Video.
System speech and AI speech are different tools
System TTS is a practical choice for longer scripts, accessibility-style reading, drafts, and straightforward narration. It uses voices made available by Apple on the device, so the exact list and availability can vary with the system language, installed voices, and OS.
ClipFlow does not send System TTS text to the ClipFlow AI voice service. Because voice assets and system behavior are controlled by Apple, this page does not promise that every voice or synthesis path is always available offline.
Related guides
Give a longer script a clear system voice.
Choose the language, tune the delivery, and turn written text into audio ready for the next step.