Access Minimaxi Voiceover

After the v3.81 patch, the built-in Minimaxi (the parent company of Conch AI) text-to-speech synthesis has been added. It supports dozens of characters and 15 languages, and also allows setting emotions, pitch, etc. It is quite usable.

Registration and login address: https://platform.minimaxi.com/login

After logging in, real-name authentication is required using a bank card number and the mobile phone number registered with the bank.

Then open the software: Menu -> TTS Settings -> Minimaxi API

For users in China, please select api.minimaxi.com in the API. If you want to use Minimaxi's international service, please select api.minimax.io. Please note that although both are Minimaxi, one is the domestic site ( https://www.minimaxi.com/audio ) and the other is the international site ( https://www.minimax.io/audio ). Their accounts, API keys, balances, etc., are not interchangeable.

Fill in the interface key in the SK field. You can create one by opening this address: https://platform.minimaxi.com/user-center/basic-information/interface-key

Note: If you have not passed real-name authentication, the test may fail.

Additionally, when using this method, please open Menu -> Tools/Options -> Advanced Options -> Voiceover Adjustment -> Set the number of simultaneous voiceovers to 1, and set the pause time after voiceover to a value greater than 25. Otherwise, you are likely to exceed the frequency limit and fail. Regular users are only allowed 3 requests per minute, which is once every 20 seconds.

Pronunciation Emotion Selection

Minimaxi supports 7 emotions: Happy, Sad, Angry, Fearful, Disgusted, Surprised, Neutral. However, testing shows the differences are not significant. If needed, you can open this interface to set it.

Finally, note that unless you have opened a corporate account with Minimaxi and have a higher level, you may frequently encounter rate limit errors. Please set a longer pause time, which can be configured in Advanced Options -> Pause after voiceover.