Skip to main content
POST
/
tts
/
conversational
Synthesize conversational speech
curl --request POST \
  --url https://app.myhero.so/tts/conversational \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "style": "<string>",
  "voice": "<string>"
}
'
"<string>"

Documentation Index

Fetch the complete documentation index at: https://developers.myhero.so/llms.txt

Use this file to discover all available pages before exploring further.

Generates text-to-speech audio in a conversational style and returns the result as a binary audio/mpeg stream. Accepts text (max 900 chars), an optional style string (defaults to “friendly and natural”), and an optional voice. Unlike synthesizeSpeech, the response body is raw MP3 bytes, not JSON.

Authorizations

​
Authorization
string
header
required

HERO personal access token

Body

application/json
​
text
string
required
Required string length: 1 - 900
​
style
string
​
voice
string

Response

Audio stream

The response is of type file.