Post-Cutoff
Search For AI agents

Resemble AIChatterbox familyCurrentSpeech and audioReleased 28 May 2025

Resemble AI Chatterbox (Turbo / Nano / Multilingual V3)

Model idResembleAI/chatterbox

PricePrice not published

Checked29 September 2026

Where it stands

94newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Weights
Weights are public under a permissive licence (MIT).

How to call it

4 ways to use Resemble AI Chatterbox (Turbo / Nano / Multilingual V3), with the model id each provider expects.

Providers, model ids, endpoints and docs for Resemble AI Chatterbox (Turbo / Nano / Multilingual V3)
ProviderModel idEndpointDocs
Hugging Face ResembleAI/chatterbox huggingface.co
Hugging Face ResembleAI/chatterbox-turbo huggingface.co
pip chatterbox-tts github.com
NVIDIA NIM resembleai/chatterbox-multilingual-tts build.nvidia.com

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input
Text and audio
Output
Audio
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
MIT
Released
28 May 2025
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Emotion exaggeration control

    Original 0.5B Chatterbox exposes an exaggeration/intensity knob plus CFG; zero-shot cloning from ~5 s.

    Source: github.com

  • Chatterbox-Turbo: one-step decoder, paralinguistic tags

    Found after launch

    350M params (Dec 2025); speech-token-to-mel decoder distilled from 10 steps to 1; native [laugh], [cough], [chuckle] tags; sub-200 ms production latency.

    Source: huggingface.co

  • Built-in PerTh watermark

    Every output carries Resemble’s imperceptible Perth neural watermark that survives MP3 compression and edits.

    Source: github.com

  • Multilingual V3 and Nano

    Found after launch

    Multilingual V3 (0.5B, 23 languages, better speaker similarity, fewer hallucinations) plus single-language fine-tune packs; Chatterbox-Nano (110M, English, ~3x real time on 8 CPU cores).

    Source: github.com

Notes

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).

Sources: https://www.resemble.ai/resources/chatterbox-multilingual-v3-tts-with-embedded-watermarking-for-25-languages , https://huggingface.co/ResembleAI/chatterbox-nano , https://github.com/resemble-ai/chatterbox , https://www.resemble.ai/learn/models/chatterbox-multilingual , https://huggingface.co/ResembleAI/chatterbox-turbo

Not yet checked against an official source: Resemble’s pricing page now centres on deepfake detection; hosted TTS price not verified.