PlayHT 2.0 Conversational is our latest Generative Text-to-Voice AI model built for conversational speech in real time.


The world’s first Large Language Text to Speech Model that’s built for carrying out conversations like a real person in real-time.

Read Our Model Release Post

AI Voices that can think and talk like humans

Key Features of PlayHT Conversational

We’ve built our Voice AI models to speak so naturally that 97% of the time it’s impossible to tell it’s an AI speaking.
Ellipse icon
Built for Conversational AI
Built for real life conversations, the model generates speech that sounds exactly like a person talking.
Ellipse icon
Voice Cloning with 30s audio
The model is capable of cloning any voice along with its accent and generating speech in the cloned voice.
Ellipse icon
Direct Voices with Emotions
The model understands emotions and is able to generate speech in a specific emotion as directed.

voice cloning

Creates perfect replica of any voice with just 30s of audio

Original voice
Cloned voice
Original voice
Cloned voice
Original voice
Cloned voice


Do real conversations with real people in real time

Voice AI for SDRs and Sales
Scale sales operations with cloned voices that can carry out full conversations or drop messages.
Voice AI for Customer Support
Serve customers 24/7/365 with emphatic voices they’ll love talking to.
Voice AI for Characters
Power your gaming characters and AI agents with expressive conversational voices.
Voice AI for Podcasts
Create entire AI Podcasts or edit existing ones using your AI Cloned Voice.


Control and direct how AI Voices speak with Emotions

Cloned voice with Happy Emotion applied
Any cloned voice can now be directed with Emotions
Sad Emotion applied
Disgust Emotion applied
Fear Emotion applied

Sign Up for Beta Access to PlayHT Conversational