Byte Volcano Speech Synthesis
Speech synthesis is the process of turning text into spoken sound. There are many excellent open-source solutions, such as GPT-SoVITS and ChatTTS, as well as the free edge-tts. Of course, there are also commercial-grade services, such as Byte Volcano's speech synthesis service. If you want to get it for free, the former is naturally the first choice, but for better quality, the latter is more suitable. Especially with the development of large models, the price is getting lower and lower, and choosing a commercial-grade API voiceover is also a good choice.
After version 2.88, the speech synthesis service of Byte Volcano Engine has been added, supporting voiceovers in 8 languages including Chinese, English, Japanese, Portuguese, Spanish, Thai, Vietnamese, and Indonesian. Under Chinese, it also supports many dialects such as Northeast dialect and Sichuan dialect. There are 20,000 free requests, which can synthesize about 10 hours of speech.
Supported Chinese Voices
Only some Chinese voices are shown. View the other 7 language voices here https://www.volcengine.com/docs/6561/97465
There are many supported Chinese voices, including various dialects and the popular Xiaoshuai Xiaomei movie commentary sounds in Douyin.
| Voice Name | voice_type |
|---|---|
| Cancan 2.0 | BV700_V2_streaming |
| Yangyang | BV705_streaming |
| Sunny Youth | BV123_streaming |
| Anti-Involution Youth | BV120_streaming |
| General Uxorilocal Son-in-law | BV119_streaming |
| Ancient Style Girl | BV115_streaming |
| Overbearing Mature Uncle | BV107_streaming |
| Simple Youth | BV100_streaming |
| Gentle Lady | BV104_streaming |
| Cheerful Youth | BV004_streaming |
| Sweet Pampered Girl | BV113_streaming |
| Refined Youth | BV102_streaming |
| Sweet Xiaoyuan | BV405_streaming |
| Friendly Female Voice | BV007_streaming |
| Intellectual Female Voice | BV009_streaming |
| Chengcheng | BV419_streaming |
| Tongtong | BV415_streaming |
| Friendly Male Voice | BV008_streaming |
| Dubbing Male Voice | BV408_streaming |
| Lazy Sheep | BV426_streaming |
| Fresh Literary Female Voice | BV428_streaming |
| Chicken Soup Female Voice | BV403_streaming |
| Wise Old Man | BV158_streaming |
| Loving Grandma | BV157_streaming |
| Rapping Guy | BR001_streaming |
| Energetic Commentary Male | BV410_streaming |
| Movie Commentary Xiaoshuai | BV411_streaming |
| Commentary Xiaoshuai-Multi Emotional | BV437_streaming |
| Movie Commentary Xiaomei | BV412_streaming |
| 纨绔 青年 | BV159_streaming |
| 直播一姐 | BV418_streaming |
| 反卷青年 | BV120_streaming |
| 沉稳解说男 | BV142_streaming |
| 潇洒青年 | BV143_streaming |
How to Enable
- Of course, you must first register, log in, and pass real-name authentication
https://console.volcengine.com/
Open this address to register and log in, and complete real-name authentication
- After entering the console, open the Speech Technology page as shown in the figure below
You can also click this address to directly enter https://console.volcengine.com/speech/app
Then create an application as shown in the figure below, fill in the name and introduction at will, the key is to select "Speech Synthesis Service", and then confirm to complete
- Next, enter the speech synthesis page to enable the free trial
Go to address https://console.volcengine.com/speech/service/8
Select the application you just created at the top, and click "Try" to enable it
- Copy 3 parameters, which can be filled in the video translation software
The first is the cluster id, copy the name under cluster id as shown in the figure
The second is the App id, scroll down on this page to see it
The third is the Access Token, copy it on the right side of App id.
- Fill in the video translation software, open the Menu - TTS Settings - Byte Volcano Speech Synthesis window to fill in, and save after testing without problems.
Using in Video Translation Software
After filling in the test without problems, first select the target language in the software, and then select Byte Volcano Speech Synthesis in the voiceover channel. You can click to listen to each tone
Select a satisfactory tone to start the voiceover operation.
Special Note
If you enable the official version, only the General Male and General Female 2 roles are available by default. Other roles need to be purchased and enabled separately in the Byte Volcano background.