Chatterbox
An MIT-licensed text-to-speech model with voice cloning, from a company that sells voice AI.
Instead of ElevenLabs
Screenshot from github.com/resemble-ai/chatterbox, taken 2026-10-30, shown to help you recognise the tool. It belongs to its maker. Ask us to remove it.
Cloning a voice from ten seconds of audio used to sound like a heist film premise, and now it is a pip install. Chatterbox from Resemble AI is MIT licensed and runs locally on CUDA, CPU or Apple silicon, with an English-only Turbo and Nano and a multilingual version that covers 23 or more languages, from Arabic to Swahili. Nano is aimed at CPUs and the page says it runs at 3 times realtime on 8 cores.
Chatterbox scores a 5 on lock-in, a 4 on self-direction, longevity and delivery and a 3 on footprint and power.
Every file it generates carries Resemble AI's Perth watermark, and the page says it is imperceptible and survives MP3 compression and editing, with a script to check for it. That serves a purpose and it also means the company's mark travels with your output, so Power is a 3. The only usage rule on the page is the line telling you not to use the model to do bad things. The page gives no hardware numbers for the larger models.
- Voice cloning and speech in 23 or more languages, run locally
- MIT licensed, from Resemble AI, a company that sells voice products
- Every output carries a Resemble AI watermark
What stands out
Do you make Chatterbox? Get the badge for your site
This badge reports a dated review. It is not a certification and it costs nothing. Link it to this page and leave the numbers alone: the image always shows the current score.
For dark backgrounds, use chatterbox-dark.svg in place of chatterbox-light.svg.
For comparison, we also reviewed ElevenLabs (16/30) as a benchmark.
Other tools for “hear text read aloud without a subscription”
KokoroA small open-weight text-to-speech model with Apache-licensed weights that runs on modest hardware.
eSpeak NGA compact speech synthesizer that covers more than a hundred languages and accents.
PiperA fast, local neural text-to-speech engine you install with one command.
SherpaTTSAn Android text-to-speech engine that uses Piper or Coqui voices and reads aloud with no connection.