Text-2-Speech

Text-2-Speech is an API that can be used when you want to get the audio for the text.

Using this api you can get the audio for any text

Path: /api/v1/speech/

Method: POST

Request Data

{
    “content”: <string>,
    "accent": <"EN_IN" | "EN_US" | "EN_UK">, // EN_IN - INDIAN, EN_US - AMERICAN, EN_UK - British
    "voice_type": <"male" | "female">,
    "num_of_words_per_minute": <number>
}

Response Data

{
    "id": <speech_id:ID>,
    "text_2_speech_status_url": "/api/v1/speech/<speech_id>/status/",
    "status": “pending” | “in_progress” | “completed” | “failed”,
    "error": <string> | <None>,
    "data": <None>
}

Example

Request Data

ch is sound vocabulary that can be used for listening exercises such as Phonetics

{
    "content": "ch",
    "accent": "EN_IN",
    "voice_type": "female",
    "num_of_words_per_minute": 100
}

Response Data

{
    "id": 3,
    "text_2_speech_status_url": "/api/v1/speech/<speech_id>/status/",
    "status": “in_progress”,
    "error": null,
    "data": null
}

Check the status of text-to-speech

Path: /api/v1/speech/<speech_id>/status/

Method: GET

Request Data

{}

Response Data

{
    "id": <speech_id:ID>,
    "text_2_speech_status_url": "/api/v1/speech/<speech_id>/status/",
    "status": “pending” | “in_progress” | “completed” | “failed”,
    "error": <string> | <None>,
    "data": {
       "audio_url": <audio_url> // .wav file
    }
}

Example

Request data

{}

Response data

{
    "id": 3,
    "text_2_speech_status_url": "/api/v1/speech/<speech_id>/status/",
    "status": “completed”,
    "error": null,
    "data": {
       "audio_url": <url> // .wav file
    }
}