Gemini TTS Voiceover Support Added in v3.70
Gemini 2.5 introduces a highly useful feature: multi-speaker text-to-speech voiceovers, implemented through the gemini-2.5-flash-preview-tts
and gemini-2.5-pro-preview-tts
models.
Open Menu -- Translation Settings -- Gemini Pro
, fill in your API key, and select the desired model in the TTS Model
dropdown at the bottom. 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
in the voiceover channel. It supports voiceovers in 24 languages and offers 30 speaker roles.
Voice Name: 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
Potential Issues and Solutions
Currently, Gemini has relatively strict API call frequency limits. When processing a large number of text lines, especially in dual-speaker mode, you may encounter generation failures (especially when the text is in Chinese), potentially encountering a 429
error, indicated by the 429
error code in the error message.
- The easiest solution is to wait a few minutes or longer before retrying, or increase the waiting time after voiceover pauses, and reduce the number of concurrent requests.
- A better solution, of course, is to subscribe to a paid Google account.
Important Notes:
- VPN/Proxy Required: To access Google AI services, you need access to the global internet (please resolve network issues yourself). This is fundamental to using foreign AI tools; otherwise, subsequent steps will not work.
- Google Account: You will need a free Google account. If you don't have one, you can register on the Google website. Typically, a domestic mobile phone number is sufficient for registration.