unknown

Resemble AI open-sourced Chatterbox Turbo, a fast text-to-speech model that runs locally with sub-150ms latency. It offers three variants: Turbo for English speed optimization, Multilingual supporting 23 languages with voice cloning, and an expressive English version. The MIT-licensed tool includes zero-shot voice cloning from 10 seconds of audio, watermarking, and expressive controls. In blind tests, it outperformed ElevenLabs in 63% of comparisons while being faster. Drawbacks include occasional overacting, tail-end audio artifacts, slow CPU performance requiring a GPU, and ethical concerns around voice cloning capabilities.

An Open-Source Alternative to ElevenLabs

Development tricks and tips. Radically better observability stack. Ship higher-quality software faster. Be the hero of your engineering teams.

Better Stack

An Open-Source Alternative to ElevenLabs

yes and its actually that good, and pared with gemini u can say get me the voice for whoever it will find clips and clean the audio if asked and get the sample and presto u got an identic voice clone.

Thanks for the post, this looks interesting.

This is interesting. Certainly a must try for setting up my homelab. Thanks for sharing