Integrating Minimaxi Dubbing in the Custom TTS API Interface

Since edge-tts is no longer as easy to use, dubbing has become much more troublesome. Free options require local deployment of GPT-SoVITS/CosyVoice/F5-TTS/Kokoro/ChatTTS, etc.

The online OpenAI TTS has a severe lisp when synthesizing Chinese, while the best online Chinese effects are currently AzureTTS/ByteDance Speech Synthesis/302.AI.

After the v3.62 patch, the Custom TTS API Interface has built-in text-to-speech from Minimaxi (the parent company of Conch AI), supporting dozens of characters and 15 languages, and can also set emotions, pitch, etc. It is considered relatively usable.

Introduction to the Access Method

There are 2 access methods: One is to access from 302.AI, which is simpler, ready to use upon registration, does not require real-name authentication, and has fewer restrictions, so it is recommended. The second is to access natively from Minimaxi.com, which is slightly more complicated and has a lower request frequency limit (3 times per minute), and also requires filling in a bank card and reserving a mobile phone number for real-name authentication.

One: Access from 302.AI

It is essentially accessing Minimaxi's dubbing, but through 302.AI, which is slightly more convenient to use. 302.AI registration address (register from this address to get a $1 credit) https://share.302.ai/pyvideo

1. First upgrade pyVideoTrans to v3.62 (upgrade address: https://pvt9.com/downpackage)
2. Then find Menu--TTS Settings--Custom TTS API, as shown in the figure below, fill in https://api.302.ai/minimaxi/v1/t2a_v2 in the API Paste the following roles in Dubbing Role Name, the dubbing roles for the two access methods are the same

Youthful Youth Voice:male-qn-qingse,
Elite Youth Voice:male-qn-jingying,
Domineering Youth Voice:male-qn-badao,
Youth College Student Voice:male-qn-daxuesheng,
Maiden Voice:female-shaonv,
Mature Woman Voice:female-yujie,
Mature Female Voice:female-chengshu,
Sweet Female Voice:female-tianmei,
Male Host:presenter_male,
Female Host:presenter_female,
Male Audiobook 1:audiobook_male_1,
Male Audiobook 2:audiobook_male_2,
Female Audiobook 1:audiobook_female_1,
Female Audiobook 2:audiobook_female_2,
Youthful Youth Voice-beta:male-qn-qingse-jingpin,
Elite Youth Voice-beta:male-qn-jingying-jingpin,
Domineering Youth Voice-beta:male-qn-badao-jingpin,
Youth College Student Voice-beta:male-qn-daxuesheng-jingpin,
Maiden Voice-beta:female-shaonv-jingpin,
Mature Woman Voice-beta:female-yujie-jingpin,
Mature Female Voice-beta:female-chengshu-jingpin,
Sweet Female Voice-beta:female-tianmei-jingpin,
Clever Boy:clever_boy,
Cute Boy:cute_boy,
Lovely Girl:lovely_girl,
Cartoon Pig Xiaoqi:cartoon_pig,
Yandere Younger Brother:bingjiao_didi,
Handsome Boyfriend:junlang_nanyou,
Innocent Junior:chunzhen_xuedi,
Aloof Senior:lengdan_xiongzhang,
Overbearing Young Master:badao_shaoye,
Sweet Little Ling:tianxin_xiaoling,
Lively Cute Girl:qiaopi_mengmei,
Charming Mature Woman:wumei_yujie,
Spoiled Junior:diadia_xuemei,
Elegant Senior:danya_xuejie,
Santa Claus:Santa_Claus,
Grinch:Grinch,
Rudolph:Rudolph,
Arnold:Arnold,
Charming Santa:Charming_Santa,
Charming Lady:Charming_Lady,
Sweet Girl:Sweet_Girl,
Cute Elf:Cute_Elf,
Attractive Girl:Attractive_Girl,
Serene Woman:Serene_Woman

Copy the API KEY from the 302.AI background and paste it into the SK of the software

The final filling is shown in the figure below. Test if the audio plays normally, indicating that the configuration is correct, save it and you can use it.

Two: Native Access to Minimaxi

Registration and login address https://platform.minimaxi.com/login After logging in, you need to verify your real name with your bank card number and bank reserved mobile phone number. After the verification is passed, open this address https://platform.minimaxi.com/user-center/basic-information Copy groupID

Then open the software Menu--TTS Settings--Custom TTS API, fill in the api address, pay attention to replace it with your groupID https://api.minimax.chat/v1/t2a_v2?GroupId=your copied groupID

Fill in the interface key in SK, you can open this address to create https://platform.minimaxi.com/user-center/basic-information/interface-key

The dubbing role filling method is the same as 302.AI, after all filling, the following figure shows

Note that if you have not passed real-name authentication, the test may fail. In addition, when using this method, please open Menu--Tools/Options--Advanced Options--Dubbing Adjustment--Set the number of simultaneous dubbings to 1, and set the pause time after dubbing to a value greater than 25, otherwise it is likely to exceed the frequency failure. Ordinary users are only allowed to request 3 times in 1 minute, that is, once every 20 seconds.

Pronunciation Language Selection

Supports 15 languages, Chinese, Cantonese, English, Spanish, French, Russian, German, Portuguese, Arabic, Italian, Japanese, Korean, Indonesian, Vietnamese, Turkish, Dutch, Ukrainian

When dubbing in the software interface, select the language of the subtitles, but note that it must be within the above 15 ranges. Only when you need Cantonese pronunciation, you need to open the Custom TTS API interface and set the language to Chinese,Yue. At other times, please make sure that auto is selected here.

Pronunciation Emotion Selection

Minimaxi supports 7 emotions: happy, sad, angry, scared, disgusted, surprised, neutral, but the test found that the difference is not significant. If necessary, you can open this interface to set it.

Finally, unless you have opened a corporate account in minimaxi and the level is high, it is recommended to use the 302.AI access method, otherwise 3 requests per minute for subtitle dubbing will either be too slow to accept, or frequently report rate limit frequency limit errors 302.AI registration address (1 USD experience credit): https://share.302.ai/pyvideo