🎙️ Live demo: Try this model in the
ResembleAI/Chatterbox-Multilingual-TTS-es-mx-latamSpace.
Chatterbox Multilingual: Latin American Spanish
Chatterbox Multilingual: Latin American Spanish is a dedicated single-language finetune in the Chatterbox Multilingual V3 Single Language Pack. It is optimized for Spanish as spoken in Latin America and Mexico, with language- and region-specific behavior for expressive text-to-speech and voice cloning.
Use this model when you want tighter Latin American Spanish 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-mx-latam.
Files
t3_es_mx_latam.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-419 / es-MX - Chatterbox language ID:
es
Checkpoint Metadata
- Source step:
138500 - Source checkpoint:
t3_138500.pth.tar - Tensor count:
292 - Dtype:
float32 - Text embedding shape:
(2454, 1024) - Speech embedding shape:
(8194, 1024) - Size:
2143990280bytes - SHA256:
c66c4517f11c2b35a56e28615c0689deb864cbc411e329552223bbd0a6a063f8
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.