Multilingual V3 coverage
According to the model card, V3 is the recommended general multilingual model with broad coverage similar to V2 and stronger stability.
Open Source Model Profile · ResembleAI
chatterbox
chatterbox is a ResembleAI multilingual text-to-speech model. The model card describes Chatterbox Multilingual V3 as a 0.5B model across 23 languages.
- Publisher
- ResembleAI
- Task
- text-to-speech
- Model type
- Unknown
- License
- mit
- Library
- chatterbox
- Publication status
- Accepted · not indexed
Model overview
chatterbox is published by ResembleAI as a text-to-speech model. Captured metadata records an mit license with a chatterbox library tag and multilingual TTS tags. According to the model card, Chatterbox Multilingual V3 is a 0.5B general multilingual model supporting 23 languages.
Recorded capabilities
Single-language pack
The model card describes dedicated finetunes for Chinese, LatAm and Spain Spanish, Brazilian and Portugal Portuguese, and Hindi.
Stability controls
According to the model card, V3 reduces continuation, repetition, and off-prompt speech, with exaggeration, CFG, and alignment-informed inference.
Voice-prompt generation
The model card documents generate calls with an optional audio prompt path for synthesizing in a different voice.
Use cases in the source record
- General multilingual speech synthesis and voice-cloning workflows with one model across many languages.
- Language-specific synthesis using the dedicated Chinese, Spanish, Portuguese, and Hindi finetunes described in the card.
Limitations and unknowns
- No structured parameter count, architecture, or model-type values were extracted; 0.5B size comes from the publisher model card.
- No independent Ethen evaluation results were extracted; quality comparisons come from the publisher model card.
- Provider state is historical snapshot data, not independently refreshed current availability.
- According to the model card, outputs are watermarked, and training-scale and backbone claims have not been independently verified by Ethen.
Source and provenance
Source: ResembleAI/chatterbox
Captured: Unknown. Processed: 2026-09-07T19:34:36.299846+00:00.
Chatterbox TTS Made with ❤️ by Latest Release: Chatterbox Multilingual V3 Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages. V3 is designed for broad language coverage like V2, but with stronger stability and more expressive generation. It is the recommended multilingual model for users who want one voice cloning model that works across many languages. Try it in the Chatterbox Multilingual TTS V3 Space . Alongside V3,…
F001F002F003F004F005F007F008F009F010F011F012F014F016