Skip to content

Resemble AI's low-latency TTS optimized for voice agents. 350M params, 1-step decoder, paralinguistic tags ([laugh], [cough]). All components q4 quantized (~720 MB).

WASM
MIT

Embed Chatterbox Turbo

Copy the code below to embed this TTS demo on your website.

<iframe src="https://ttslab.dev/embed/chatterbox-turbo" width="100%" height="400" frameborder="0" allow="autoplay"></iframe>

Try It

Chatterbox Turbo
Not loaded(720.0 MB)
0 / 5000

Try an example

Recent generations

No generations yet. Generate speech above to see your history here.

Technical Details

Architecture

Chatterbox Turbo (GPT-2 backbone)

Parameters

350M

Model Size

720 MB

Voices

1

Languages

en

Links