Frequently asked questions

VoiceFlow AI is an iPhone app that turns text into lifelike, emotional speech, in one voice or a dialogue of up to 10 voices. It also reads PDFs aloud, transcribes recordings, removes background noise and generates sound effects.

VoiceFlow AI is free to download, and every tool and every voice model, including the expressive v3 voices and multi-voice Dialogue, is open to everyone. Free tokens arrive every week. If you need more, you choose how to pay: token packs that never expire, like pay as you go, or an optional Premium plan.

No. Token packs work like pay as you go: you buy them once and they never expire. Premium is optional. It gives a larger token allowance for the money and renews each billing cycle. Every tool and voice model, including v3 and Dialogue, is open without it.

No. There is no sign-up. Every tool opens the moment you install the app.

No. VoiceFlow AI is an iPhone app, available on the App Store. It needs iOS 17 or later.

Tokens are how VoiceFlow AI measures use. Longer texts and longer recordings use more tokens, and the app shows the cost before you generate. Free tokens arrive every week.

Voices speak 31 languages: English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Ukrainian, Russian, Hungarian, Norwegian, Vietnamese. The app itself is available in English, Turkish, German, Spanish, French, Portuguese (Brazil).

No. VoiceFlow AI (voiceflow-ai.com) is an independent iPhone app for AI voices and audio. It is not related to Voiceflow, the platform for building conversational AI agents.

Many creators use VoiceFlow AI audio in videos, podcasts and client work. See the in-app terms for the details that apply to your use.

Yes. Every voice model, including v3 with emotion tags, is open to everyone, with free tokens every week. If you need more, buy a token pack that never expires.

Yes. On the v3 model you write a tag such as [excited], [whispers], [laughs], [sad], [sarcastic] or [shouts] before a line and the voice performs that emotion. The app has 27 ready-made tags, and v3 is open to everyone.

Yes. Dialogue lets you write a script with up to 10 voices, give each line its own emotion, and generate one audio file with every voice in it.

English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Ukrainian, Russian, Hungarian, Norwegian, Vietnamese.

Many creators use VoiceFlow AI voiceovers in social videos, podcasts and client work. Check the in-app terms for the details that apply to your use.

Up to 10 different voices in one script.

No. Dialogue gives you one finished audio file with every voice in it, ready to share.

Yes. iOS has a basic Speak Screen feature, and VoiceFlow AI Reader goes further with natural AI voices, word by word highlighting and a document library that remembers your place.

Yes. Scan a printed page with the camera and the Reader recognises the text and reads it aloud.

Share or import the recording into VoiceFlow AI Speech to Text. It transcribes the audio, labels the speakers and lets you copy or share the text.

Yes. Transcripts are labelled speaker by speaker, and you can rename each speaker.

Yes. Pick a video from your photo library and VoiceFlow AI transcribes its audio.

Import the video into VoiceFlow AI Voice Isolator. It extracts the voice and removes the background noise, and you can save the clean audio.

Yes. Describe the sound in plain words and VoiceFlow AI generates it as an audio file in seconds.