Enter the script
Type text or import a plain-text file. A single generation can contain up to 1,000 characters.
System + Pro AI · iPhone + iPad
Turn text into audio with system or AI voices.
Type or import up to 1,000 characters, then switch between Apple system voices and ClipFlow Pro AI voices in the same workspace. Each mode keeps the controls that fit its speech service.
One script, two voice modes
How to convert text to speech on iPhone.
Choose System for Apple voices or AI for ClipFlow Pro's online voice service without leaving the workspace.
Choose the voice mode
Use the segmented control to switch between System and AI. Switching to AI requires ClipFlow Pro; System mode remains available without Pro.
Adjust the delivery
In System mode, choose one of eight supported languages and set rate and pitch. In AI mode, choose an AI voice and optionally begin the text with a parenthetical cue for emotion, tone, dialect, or singing.
Generate the audio
Create the speech result, then save it, trim it, change its speed, insert pauses, or use Add to Video.
Each mode keeps its own service boundary
System mode uses voices made available through Apple's system speech capabilities. ClipFlow does not send text entered for a System-mode generation to the ClipFlow AI voice service. Voice availability can vary with the system language, installed voices, device, and OS.
AI mode requires ClipFlow Pro and an internet connection. It sends the input text, selected voice, and necessary pseudonymous purchase-entitlement and technical identifiers to ClipFlow's TTS service for generation, entitlement verification, quota enforcement, safety, and abuse prevention. The text and voice are provided to the current speech supplier, Xiaomi MiMo. Do not enter sensitive information that you do not want submitted to an online service.