After v3.70, the software has added support for dubbing using Gemini TTS
Gemini 2.5 introduces a very practical new feature: multi-speaker text-to-speech dubbing, implemented by the gemini-2.5-flash-preview-tts and gemini-2.5-pro-preview-tts models.
Open Menu -- Translation Settings -- Gemini Pro, fill in your key, and in the TTS Model section at the bottom, select which model to use. It is recommended to use the gemini-2.5-flash-preview-tts model, as it has fewer restrictions and a higher free quota.
Then, in the software interface, select Gemini TTS as the dubbing channel. It supports dubbing in 24 languages and offers 30 speaker roles.
Voice names: Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima, Achird, Zubenelgenubi, Vindemiatrix, Sadachbia, Sadaltager, Sulafat
Possible Issues and Solutions
Currently, Gemini has relatively strict rate limits on API calls. When you process a large number of text lines, especially in dual-speaker mode, you might encounter generation failures (especially when the text is in Chinese). You might encounter a 429 error, meaning the error message contains the 429 error code.
The simplest method is to wait a few minutes or longer before trying again, or increase the waiting time after dubbing pauses and reduce the concurrency.
Important Notes:
- Internet Access (VPN/Proxy): To access Google AI services, you need to be able to access the international internet (please resolve network issues yourself). This is fundamental for using foreign AI tools; otherwise, subsequent steps cannot be performed.
- Google Account: You need a free Google account. If you don't have one, you can register on the Google official website; typically, a domestic mobile number is sufficient for registration.