Model profile

Chatterbox

Audio Generation

Reference-audio text-to-speech for cloning delivery style, creator narration, and character-driven voice work.

Lab

Resemble AI

First announced

June 2, 2025

Available apps

1 product pages

All models Product pages

Model background

Documented by fal.ai when Resemble AI’s open-source Chatterbox text-to-speech model became available through the Fal platform with optional reference-audio prompting.

Lab: Resemble AI

First announced: June 2, 2025

Best uses

Reference-audio voice styling
Adjustable exaggeration, temperature, and CFG controls
Useful for narration, character reads, and creator voice workflows

Output types

Audio

Primary sources

fal.ai: Chatterbox Text to Speech fal Blog: Chatterbox Available on Fal Resemble AI: Chatterbox

Available in creator apps

Text to Speech

Turn scripts and captions into spoken audio in minutes.

Open product page Open app