Text turned into speech
You type the text and the model converts it into a generated speech audio clip.
Clone a voice
Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.
Opens the audio studio with Dia Tts Voice Cloning ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What it makes
Clone a voice
Learns a voice from a short sample so you can reuse it.
What you need
What you get
A reusable voice that sounds like the sample
Dia Tts Voice Cloning, made by Nari Labs, is a text-to-speech model: you type text and get spoken audio back. The result is a generated speech audio clip.
Text is the one input you provide. Write the words you want spoken in the Text box and the model converts them into speech. Text is the only field to fill in, and no audio file is needed.
Choose it when you have a line or a script you want to hear read aloud. A run costs 100 credits.
Same job: clone a voice. Compare before you choose.
Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!
Create Voices to be used with Kling Models Voice Control
Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!
You type the text and the model converts it into a generated speech audio clip.
Text is the only field you fill in. You add no audio file.
Type the words you want spoken into the Text box.
Press generate. A run costs 100 credits.
Listen to the generated speech audio when it is ready.
Type the narration and get it back as a speech audio clip.
Write lines of dialog and hear them read aloud.
Turn a written note or announcement into audio you can play.
Quick answers to help you get the most out of Dia Tts Voice Cloning in FunAI Studio.