The TTS Text upload generate API allows you to upload text and wait to get the audio file as a response.
This endpoint only supports text less than or equal to 4096 characters
This endpoint requires an Integrator Account

​
Rate Limits

30 requests per minute
Rate limit headers included in response
Retry-After: (delay-seconds) indicates time in seconds to retry

​
Endpoint

POST https://infer.voice.intron.io/tts/v1/generate

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Headers

HeaderValueRequired
AuthorizationBearer YOUR_API_KEYYes
Content-Typeapplication/jsonYes

​
Body Parameters

FieldTypeDescriptionRequiredOptionsDefault
textStringthe text to processyes
voice_accentStringAccent for the speech voiceyessee page of supported accents
voice_genderStringAccent for the speech voiceyesmale / female
voice_languageStringLanguage of the input textnosee page of supported languagesen
output_audio_formatStringSpecify the output audio formatnosee list of supported audio formats belowwav

​
Supported Output Audio Formats

FormatExtensions
WAV.wav
OPUS.opus

​
Supported Language And Accents

Supported Languages And Accents

Comprehensive list of languages and accents supported

​
Basic request and response sample

​
Requests

curl --location 'https://infer.voice.intron.io/tts/v1/generate' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer api-key' \
--data '{
    "text":"hello world",
    "voice_language":"en",
    "voice_accent":"swahili",
    "voice_gender":"female"
}'

​
Response

The request can timeout with an http status code 503 in 120 seconds, the text-id in the 503 response can be used to get the file’s status with the Get TTS Status endpoint
{
    "data": {
        "audio_duration_in_seconds": 3,
        "audio_path": "http://myaudio.wav",
        "processing_status": "TTS_TEXT_AUDIO_GENERATED"
    },
    "message": "text status found",
    "status": "Ok"
}

​
Error Responses

Error response if the max character limit is exceed, Please refer to the list of support language,accent lists Supported Voice language and accents
JSON
{
    "data": {},
    "message": "tts text character count greater than the max limit of 100 characters",
    "status": "Error"
}
Error response if an unsupported language code was sent, Please refer to the list of support language,accent lists Supported Voice language and accents
JSON
{
    "data": {},
    "message": "invalid text voice language,{language} not supported",
    "status": "Error"
}
Error response if the voice_accent sent is not supported under the selected voice_language, Please refer to the list of support language,accent lists Supported Voice language and accents
JSON
{
    "data": {},
    "message": "invalid text voice accent,{accent} not supported for language {language}",
    "status": "Error"
}
Error response if the voice_gender sent is not supported under the selected voice_accent, Please refer to the list of support language,accent lists Supported Voice language and accents
JSON
{
    "data": {},
    "message": "invalid text voice gender,{gender} not supported for accent {accent}",
    "status": "Error"
}
Error response if the output_audio_format is not supported, Please refer to the list of supported output_audio_format above
JSON
{
    "data": {},
    "message": "invalid text voice gender,{gender} not supported for accent {accent}",
    "status": "Error"
}