Post-Cutoff.com
  1. Home
  2. Models
  3. Resemble AI Chatterbox (Turbo / Nano / Multilingual V3)

Resemble AI Chatterbox (Turbo / Nano / Multilingual V3)

Resemble AIcurrentaudio/speechChatterboxopen weights

All MIT-licensed. Multilingual (23 langs) first released Sept 2025. Multilingual V3 released 2026-06-10 (Resemble post; V3 T3 weights first pushed to HF 2026-04-22): same 0.5B Llama backbone, training data up from 25.6k to 36.7k hours, 25 languages incl. 4 dialects and 6 tuned Language Pack models, PerTh watermark on by default; Resemble reports CER under 0.20% for Italian/German but ~71-75% for Korean/Vietnamese (not production-ready); NVIDIA NIM claims 2x-39x throughput. Chatterbox-Nano HF repo created 2026-04-14 (public announcement date not found). Artificial Analysis lists Chatterbox at ~1020 Elo (secondary source). Resemble's pricing page now centres on deepfake detection; hosted TTS price not verified.

Input
text, audio
Output
audio
License
mit
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
Hugging FaceResembleAI/chatterboxhuggingface.co/ResembleAI/chatterbox—
Hugging FaceResembleAI/chatterbox-turbohuggingface.co/ResembleAI/chatterbox-turbo—
pipchatterbox-ttsgithub.com/resemble-ai/chatterbox—
NVIDIA NIMresembleai/chatterbox-multilingual-ttsbuild.nvidia.com/resembleai/chatterbox-multilingual-tts/modelcard—

Notable capabilities (4)