Skip to main content
POST
/
tasks
/
modal
/
tts
Generate Text-to-Speech Audio
curl --request POST \
  --url https://api.sunbird.ai/tasks/modal/tts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "speaker_id": 248,
  "response_mode": "url"
}
'
{
  "success": true,
  "audio_url": "<string>",
  "expires_at": "2023-11-07T05:31:56Z",
  "file_name": "<string>",
  "duration_estimate_seconds": 123,
  "text_length": 123,
  "speaker_id": 241,
  "speaker_name": "<string>"
}

Authorizations

​
Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

Request model for TTS generation.

​
text
string
required

Text to convert to speech

Required string length: 1 - 10000
Example:

"Hello, this is a text-to-speech test."

​
speaker_id
enum<integer>
default:248

Speaker voice for TTS generation

Available options:
241,
242,
243,
245,
246,
248
Examples:

248

246

​
response_mode
enum<string>
default:url

How to return the audio: 'url' for signed URL, 'stream' for streaming, 'both' for streaming with final URL

Available options:
url,
stream,
both

Response

Audio generated successfully

Response model for TTS generation (URL mode).

​
success
boolean
required

Whether the request was successful

​
audio_url
string
required

Signed URL to access the audio file

​
expires_at
string<date-time>
required

When the signed URL expires

​
file_name
string
required

Name of the audio file in storage

​
duration_estimate_seconds
number | null

Estimated audio duration in seconds

​
text_length
integer | null

Length of the input text

​
speaker_id
enum<integer> | null

Speaker voice used for generation

Available options:
241,
242,
243,
245,
246,
248
​
speaker_name
string | null

Human-readable speaker name