Text To Speech API
All the available APIs needed to generate audio from text.
post
https://api.convai.com/tts
/
Convai's Text-To-Speech API endpoint
Voice Type / ID | Name | Format Supported |
|---|---|---|
MALE | High quality US Masculine Voice | wav |
FEMALE | High quality US Feminine Voice | wav |
WUKMale 1 | Young UK Masculine Voice | wav, mp3 |
WUKMale 2 | Middle-aged UK Masculine Voice | wav, mp3 |
WUKFemale 1 | Flat UK Feminine Voice | wav, mp3 |
WUKFemale 2 | Heavy UK Feminine Voice | wav, mp3 |
WUKFemale 3 | Young UK Feminine Voice | wav, mp3 |
WAMale 1 | Young Australian Masculine Voice | wav, mp3 |
WAMale 2 | Middle-aged Australian Masculine Voice | wav, mp3 |
WAFemale 1 | Midlle-aged Australian Feminine Voice | wav, mp3 |
WAFemale 2 | Young Australian Feminine Voice | wav, mp3 |
WIMale 1 | Young Indian Masculine Voice | wav, mp3 |
WIMale 2 | Heavy Indian Masculine Voice | wav, mp3 |
WIFemale 1 | Young Indian Feminine Voice | wav, mp3 |
WIFemale 2 | Heavy Indian Feminine Voice | wav, mp3 |
WUMale 1 | Robotic US Masculine Voice | wav, mp3 |
WUMale 2 | Middle-ages US Masculine Voice | wav, mp3 |
WUMale 3 | Young US Masculine Voice | wav, mp3 |
WUMale 4 | Deep US Masculine Voice | wav, mp3 |
WUMale 5 | Heavy US Masculine Voice | wav, mp3 |
WUFemale 1 | Calm US Feminine Voice | wav, mp3 |
WUFemale 2 | Middle-aged US Feminine Voice | wav, mp3 |
WUFemale 3 | Young US Feminine Voice | wav, mp3 |
WUFemale 4 | Flast US Feminine Voice | wav, mp3 |
WUFemale 5 | Sharp US Feminine Voice | wav, mp3 |
Trixie | Trixie from My Little Pony | wav |
Twilight Sparkle | Twilight Sparkle from My Little Pony | wav |
Celestia | Celestia from My Little Pony | wav |
Spike | Spike from My Little Pony | wav |
Applejack | Applejack from My Little Pony | wav |
Please note if an unsupported audio encoding is specified along with a voice in the request body, it will result in a 400 error response.
Here are some sample codes to demonstrate the request format for the endpoint -->
Python
cURL
import requests
import json
url = "https://api.convai.com/tts/"
payload = json.dumps({
"transcript": "Hello World from us",
"voice": "WUMale 1",
"filename": "testAudio",
"encoding": "mp3"
})
headers = {
'CONVAI-API-KEY': '<your api key>',
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
with open('testAudio.mp3','wb') as f:
f.write(response.content)
curl --location --request POST 'https://api.convai.com/tts' \
--header 'CONVAI-API-KEY: <your api key>' \
--header 'Content-Type: application/json' \
--data-raw '{
"transcript": "Hello World from us",
"voice": "WUMale 1",
"filename": "testAudio",
"encoding" : "mp3"
}' \
--output testAudio.mp3
Last modified 6mo ago