Text read aloud
The Prompt you enter comes back as a spoken audio clip.
Turn text into speech
Fast, lightweight TTS (no cloning)
Opens the audio studio with Piper ready to use. You will need a free account to run it.
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
Piper is a text-to-speech model. You enter text, and it returns an audio clip of that text spoken aloud. Piper does not clone voices, so it cannot copy how a particular person sounds.
You provide the text as the Prompt. You can also pick a voice with the Voice option. Type or paste the text you want spoken, then run the model to hear it.
Piper costs 200 credits. Kokoro TTS (Italian) and Kokoro TTS (French) cost 100 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.
The Prompt you enter comes back as a spoken audio clip.
The Voice option sets which voice reads your Prompt.
Type or paste the words you want spoken into the Prompt.
Use the Voice option to pick a voice.
Generate, then play the result to hear your text read aloud.
Hear a draft, message or note spoken back to you.
Add spoken narration to a video or a slideshow.
Quick answers to help you get the most out of Piper in FunAI Studio.