Text to Speech API

This page explains how to interact with the standalone Text-to-Speech (TTS) API to generate audio from a given transcript, using a selected voice from the available voice list.

This API is available only on the Enterprise Plan.

Generate Audio from Text

POST https://api.convai.com/tts/

---

Headers

CONVAI-API_KEY*	String	Your Convai API Key.
Content-Type*	String	application/json

---

Request Body

Name	Type	Description
transcript*	String	The text to be converted into audio.
voice*	String	Specifies the type of voice used for the audio response. This can be retrieved using the Voice List API, from the voice_value attribute of the desired voice. NOTE : Realtime voices are not supported in the standalone TTS API endpoint.
filename	String	The name of the audio file.
encoding	String	This is the format of the audio file. We currently support WAV and MP3 formats for STT (speech-to-text) audio. By default, it is set to WAV. NOTE : MP3 is not supported by all voices.

---

Response

If the API call is successful, it returns the generated audio file as the response.

---

Sample Code Snippet

Python

import requests
import json

url = "https://api.convai.com/tts/"

payload = json.dumps({
  "transcript": "In the quiet of the morning, as the sky turned shades of pink and orange, she walked along the path lined with blooming flowers, feeling the cool breeze on her face. It was finally time for dinner.",
  "voice": "fable_OpenAi_c4d30a32-bcaf-4048-b7b0-0f2bb293205a",
  "encoding": "wav"
})

headers = {
  'CONVAI-API-KEY': '<Your Convai API Key>',
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

if response.status_code == 200:
    with open('audio.wav','wb') as f:
      f.write(response.content)
else:
    print(response.text)