All tasks / Models
Chatterbox Multilingual V3
Resemble AI's MIT-licensed open text-to-speech models with zero-shot voice cloning; Multilingual V3 covers 23+ languages.
- Resemble AI
- Open weights
- Released Jun 2026
Where it ranks
- –Text to speechModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Resemble AI
- Family
- Chatterbox
- Released
- Jun 2026
- Weights
- Open: download and run it yourself
- License
- MIT
- Parameters
- 0.5B
- GPU memory to run locally
- ~2 GB (Derived: 0.5B parameters (README) x 2 bytes = ~1 GB of bf16 weights; Turbo (350M) and Nano (110M, CPU) variants are smaller.)
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Benchmark results
No public benchmark results recorded yet.
Where you can use it
Earlier versions
- Chatterbox Multilingual V2 · Sep 2025
- Chatterbox · 28 May 2025