# Yating TTS SDK - Python version
## Available Key
- Please contact Yating TTS
### Input
```JSON
{
"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"
}
}
```
## Available Variable
### Input Type
| Name | Description |
| ---- | ------------------------------------ |
| text | Recognize input.text as pure text. |
| ssml | Recognize input.text in ssml format. |
### Voice Setting
| 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 |
### Voice Model
| 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 |
| tai_female_1 | 16k | Yating speak Taiwanese |
| tai_female_2 | 16k | Yiqing speak Taiwanese |
| tai_male_1 | 16k | Jiahao speak Taiwanese |
### Encoding Format
| Name | File Extension | Description |
| -------- | -------------- | --------------------------- |
| MP3 | .mp3 | Compressed audio |
| LINEAR16 | .wav | Uncompromised audio quality |
### Sampling Rate
| Name | Description |
| ---- | ---------------------- |
| 16K | Sampling rate in 16khz |
| 22K | Sampling rate in 22khz |
Raw data
{
"_id": null,
"home_page": "https://github.com/pinkeyu7/yating-tts-sdk-python",
"name": "Yating-TTS-SDK-Python",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "text to speech",
"author": "pinkeyu7",
"author_email": "pinke.yu7@gmail.com",
"download_url": "",
"platform": null,
"description": "# Yating TTS SDK - Python version\n\n## Available Key\n\n- Please contact Yating TTS\n\n### Input\n\n```JSON\n{\n \"input\": {\n \"text\": \"sentence, the text that you want to generate audio\",\n \"type\": \"text\"\n },\n \"voice\": {\n \"model\": \"zh_en_female_1\",\n \"speed\": 1,\n \"pitch\": 1,\n \"energy\": 1\n },\n \"audioConfig\": {\n \"encoding\": \"LINEAR16\",\n \"sampleRate\": \"16K\"\n }\n}\n```\n\n## Available Variable\n\n### Input Type\n\n| Name | Description |\n| ---- | ------------------------------------ |\n| text | Recognize input.text as pure text. |\n| ssml | Recognize input.text in ssml format. |\n\n### Voice Setting\n\n| Name | Type | Value Limit | Description |\n| ------ | ------ | :----------: | -------------------------------- |\n| model | string | Table bellow | Voice Model |\n| speed | float | 0.5 - 1.5 | Voice Speed, faster slower |\n| pitch | float | 0.5 - 1.5 | Voice Pitch, higher or lower |\n| energy | float | 0.5 - 1.5 | Voice Energy, stronger or weaker |\n\n### Voice Model\n\n| Name | Sample Rate | Description |\n| -------------- | ----------- | --------------------------------- |\n| zh_en_female_1 | 16k,22k | Yating speak Mandarin and English |\n| zh_en_female_2 | 16k,22k | Yiqing speak Mandarin and English |\n| zh_en_male_1 | 16k,22k | Jiahao speak Mandarin and English |\n| tai_female_1 | 16k | Yating speak Taiwanese |\n| tai_female_2 | 16k | Yiqing speak Taiwanese |\n| tai_male_1 | 16k | Jiahao speak Taiwanese |\n\n### Encoding Format\n\n| Name | File Extension | Description |\n| -------- | -------------- | --------------------------- |\n| MP3 | .mp3 | Compressed audio |\n| LINEAR16 | .wav | Uncompromised audio quality |\n\n### Sampling Rate\n\n| Name | Description |\n| ---- | ---------------------- |\n| 16K | Sampling rate in 16khz |\n| 22K | Sampling rate in 22khz |\n",
"bugtrack_url": null,
"license": "",
"summary": "Yating TTS SDK Python",
"version": "1.0.4",
"project_urls": {
"Homepage": "https://github.com/pinkeyu7/yating-tts-sdk-python"
},
"split_keywords": [
"text",
"to",
"speech"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fb73213891d5bdd8771351eb244c5df116ff0c0a803fe537a93940dcf20f858e",
"md5": "a7d92635b75ba4b0d6c3442d0b2dddd9",
"sha256": "70e1864e00f424ed9c6f03bdf947345858cb39e13faedeb76c24cd3869cb1fac"
},
"downloads": -1,
"filename": "Yating_TTS_SDK_Python-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a7d92635b75ba4b0d6c3442d0b2dddd9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 4508,
"upload_time": "2023-10-20T10:42:14",
"upload_time_iso_8601": "2023-10-20T10:42:14.002690Z",
"url": "https://files.pythonhosted.org/packages/fb/73/213891d5bdd8771351eb244c5df116ff0c0a803fe537a93940dcf20f858e/Yating_TTS_SDK_Python-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-20 10:42:14",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "pinkeyu7",
"github_project": "yating-tts-sdk-python",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "yating-tts-sdk-python"
}