Model reference · open weights

Chatterbox-Multilingual-es-es

Audio ResembleAI Text→speech 1 build Open weights 0 dl/mo

Chatterbox-Multilingual-es-es is an open-weight audio or speech model from ResembleAI. Chatterbox-Multilingual-es-es (BF16) weighs 3.2 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • Chatterbox-Multilingual-es-es is a text-to-speech model developed by ResembleAI that is optimized for Spanish as spoken in Spain.
  • It supports expressive text-to-speech and voice cloning tasks and is released under the MIT license.
  • The model checkpoint has a size of 2143990264 bytes and uses a text embedding shape of (2454, 1024) with a speech embedding shape of (8194, 1024).

Summary of the ResembleAI/Chatterbox-Multilingual-es-es model card, 2026-10-01

What it is

Released byResembleAI
Released2026-04-22
VRAM3.2 GB for the weights

What it runs on

Memory and cards for Chatterbox-Multilingual-es-es (BF16)

3.2 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What ResembleAI says about Chatterbox-Multilingual-es-es

Read the model card

🎙️ Live demo: Try this model in the ResembleAI/Chatterbox-Multilingual-TTS-es-es Space.

Chatterbox Multilingual: Spanish (Spain)

Chatterbox Multilingual: Spanish (Spain) is a dedicated single-language finetune in the Chatterbox Multilingual V3 Single Language Pack. It is optimized for Spanish as spoken in Spain, with language- and region-specific behavior for expressive text-to-speech and voice cloning.

Use this model when you want tighter Spanish (Spain) quality control than the broad multilingual checkpoint. For a single model that covers all supported languages, use ResembleAI/chatterbox.

Demo

Try the hosted demo Space: ResembleAI/Chatterbox-Multilingual-TTS-es-es.

Files

  • t3_es_es.safetensors: T3 state dict in safetensors format.
  • s3gen_v3.pt / s3gen_v3.safetensors: V3 S3Gen speech decoder checkpoint.
  • grapheme_mtl_merged_expanded_v1.json: multilingual tokenizer config.

Language

  • Locale: es-ES
  • Chatterbox language ID: es

Checkpoint Metadata

  • Source step: 135500
  • Source checkpoint: t3_135500.pth.tar
  • Tensor count: 292
  • Dtype: float32
  • Text embedding shape: (2454, 1024)
  • Speech embedding shape: (8194, 1024)
  • Size: 2143990264 bytes
  • SHA256: d85844b13ea8cb45e95b8d84a55bcfeccb2d743035cf304ee3d778fc6be39546

Loader Notes

This repository contains Chatterbox Multilingual V3 single-language assets used by the linked demo Space. The T3 checkpoint is loaded with multilingual vocabulary shape 2454 and S3 speech vocabulary shape 8194.

The demo combines these model-specific assets with the shared Chatterbox inference code and companion assets needed for end-to-end speech generation.

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms