POST
/
tts
/
generate
curl --request POST \
  --url https://api.bolna.dev/tts/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "text": "The Answer to the Ultimate Question of Life, the Universe, and Everything is 42.",
  "provider": "polly",
  "provider_config": {
    "voice": "Kajal",
    "engine": "neural",
    "language": "en-US"
  }
}'
{
  "data": "UklGRkgAAABXQVZFZm10IBAAAAABAAEAgD4AAAB9AAACABAATElTVBoAAA"
}

Generating text-to-speech samples using APIs is currently live for Enterprises only.
We are slowly rolling it out to all users.

Please contact us at founders@bolna.dev for activation.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
text
string
required

String that needs to be converted to audio

Example:

"The Answer to the Ultimate Question of Life, the Universe, and Everything is 42."

​
provider
enum<string>
required

Voice provider

Available options:
polly,
elevenlabs,
deepgram
​
provider_config
object
required

Voice provider options

Response

200
application/json
Base64 encoded audio data
​
data
string

Base64 encoded audio string

Example:

"UklGRkgAAABXQVZFZm10IBAAAAABAAEAgD4AAAB9AAACABAATElTVBoAAA"

Previous
User APIs overview
Next