Gemini TTS Voiceover Support Now Available in v3.70+
Gemini 2.5 has introduced a highly useful feature: multi-speaker text-to-speech. This functionality is powered by the gemini-2.5-flash-preview-tts and gemini-2.5-pro-preview-tts models.
To use this feature, navigate to Menu -- Translation Settings -- Gemini Pro. Enter your API key and select your desired model from the TTS Model dropdown menu. The gemini-2.5-flash-preview-tts model is recommended due to its fewer restrictions and higher free tier.
Then, within the software interface, choose Gemini TTS in the voiceover channel. It supports 24 languages and offers 30 different voice actor characters.
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
Potential Issues and Solutions
Currently, Gemini has strict API call frequency limits. When processing a large number of text lines, especially in dual-speaker mode, you might encounter generation failures (particularly with Chinese text). This could result in a 429 error, indicated by the error code 429 in the error message.
- The simplest solution is to wait a few minutes or longer and try again, or increase the wait time after a voiceover pause and reduce the number of concurrent processes.
- A better solution is to subscribe to a paid Google account.
Important Notes:
- Internet Access (VPN Required): To access Google AI services, you need to be able to access the global internet (resolve network issues yourself). This is essential for using foreign AI tools; otherwise, subsequent steps will be impossible.
- Google Account: You will need a free Google account. If you do not already have one, you can register on the Google website. Registration can typically be completed using a phone number.