Yating TTS SDK - Python version
Initial Install
pip install Yating-TTS-SDK
Upgrade existed package
pip install Yating-TTS-SDK --upgrade
Yating-TTS-SDK
- Please contact Yating TTS
{
"input": {
"text": "sentence, the text that you want to generate audio",
"type": "text"
},
"voice": {
"model": "zh_en_female_1",
"speed": 1,
"pitch": 1,
"energy": 1
},
"audioConfig": {
"encoding": "LINEAR16",
"sampleRate": "16K"
}
}
Name |
Description |
text |
Recognize input.text as pure text. |
ssml |
Recognize input.text in ssml format. |
Name |
Type |
Value Limit |
Description |
model |
string |
Table bellow |
Voice Model |
speed |
float |
0.5 - 1.5 |
Voice Speed, faster slower |
pitch |
float |
0.5 - 1.5 |
Voice Pitch, higher or lower |
energy |
float |
0.5 - 1.5 |
Voice Energy, stronger or weaker |
Name |
Sample Rate |
Description |
zh_en_female_1 |
16k,22k |
Yating speak Mandarin and English |
zh_en_female_2 |
16k,22k |
Yiqing speak Mandarin and English |
zh_en_male_1 |
16k,22k |
Jiahao speak Mandarin and English |
zh_en_male_2 |
22k |
Zhiming speak Mandarin and English |
tai_female_1 |
16k |
Yating speak Taiwanese |
tai_female_2 |
16k |
Yiqing speak Taiwanese |
tai_male_1 |
16k |
Jiahao speak Taiwanese |
Name |
File Extension |
Description |
MP3 |
.mp3 |
Compressed audio |
LINEAR16 |
.wav |
Uncompromised audio quality |
Name |
Description |
16K |
Sampling rate in 16khz |
22K |
Sampling rate in 22khz |