How to make AI voices talk to each other
Short answer
To make AI voices talk to each other on iPhone, open Dialogue in VoiceFlow AI, write the script one line per turn, assign a voice to each speaker (up to 10), add emotion tags like [laughs] or [curious] where you want them, and generate. You get one audio file with the whole conversation, no editing timeline needed.
Step by step
- Install VoiceFlow AI and open Dialogue.
- Write the scene one line per turn, like a screenplay.
- Pick a voice for each speaker. Mix languages and accents if you like.
- Add a tag to any line: [excited], [whispers], [sarcastic], [sighs].
- Generate one take and share it to your editor, podcast or social app.
Ideas that work well
Skits and sketches, fake interviews and podcast intros, ad drafts with a customer and a narrator, language learning dialogues, and story or game prototypes with a full cast.
Hear it
Several voices, one take
One voice, any emotion
- [excited] We did it! The whole thing is finally ready, I can’t believe it!
- [whispers] Come closer. I’ll tell you a secret, but you can’t tell anyone.
- [laughs] No way, you actually wore that to the meeting? That’s brilliant!
- [sarcastic] Oh, great. Another Monday meeting. Exactly what I was hoping for.
- [sad] I kept the light on all night, but you never came home.
- [shouts] Hey, wait! Don’t you dare leave without me, I’m coming!
Untouched clips from the app. Voice: Hope, v3 model.
21 more tags in the app
Same line, three voice models
“Wait, you made this yourself? Honestly, it sounds just like a real person.” Flash is fastest, v2 the most lifelike for long reads, v3 the most expressive. All three are open to everyone.