Dialogue from a transcript
Turn written text into spoken dialogue.
Turn text into speech
Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.
Opens the audio studio with Dia ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What it makes
Turn text into speech
Reads your text aloud in a natural-sounding voice.
What you need
What you get
A spoken audio clip of your text
Dia turns a written transcript into spoken dialogue. You type the text and get back an audio file of the generated speech. Dia is made by Nari Labs.
It can produce nonverbal sounds as part of the speech, such as laughter and throat clearing. The only thing you provide is the text to be converted to speech. You enter it in the Text field, and the whole transcript goes in that one field.
Dia costs 20 credits.
Same job: turn text into speech. Compare before you choose.
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.
A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.
A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.
Turn written text into spoken dialogue.
Dia can produce laughter and throat clearing as part of the speech.
Type out the conversation or script you want spoken.
Put the whole transcript in the Text field.
Generate the speech to get an audio file back.
Turn a written conversation into audio you can listen to.
Get spoken dialogue that can include laughter and throat clearing.
Quick answers to help you get the most out of Dia in FunAI Studio.