FireRedTeam / FireRedTTS3
FireRedTTS3
Reference voice speech across 24 languages
Windows only
Languages
24
Chinese dialects
21
License
Apache 2.0
Platform
Windows only
Model overview
Built into OpenVox for private local voice generation.
FireRedTTS3 is a multilingual speech generation family for reference voice synthesis, with broad language and Chinese dialect coverage.
FireRedTTS3-Base supports zero-shot reference voice cloning across 24 languages and 21 Chinese dialects.
The model is designed to preserve speaker identity while generating speech in the selected language or dialect.
For the strongest cloning results, use a clear reference recording in the same language or dialect as the output.
In OpenVox, FireRedTTS3 is available on Windows and runs locally after its model files are downloaded.
OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.
Open-source model: FireRedTeam / FireRedTTS3
View on Hugging Face