Skip to main content
POST
/
v1
/
audio
/
speech
Text-to-Speech
curl --request POST \
  --url https://tts.freyavoice.ai/v1/audio/speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "tts-1",
  "input": "Hello, testing Freya Voice API.",
  "voice": "leyla"
}
'
"<string>"

Authorizations

​
Authorization
string
header
required

Bearer token issued by your workspace.

Body

application/json
​
input
string
required

The text to synthesize audio for.

​
voice
enum<string>
default:leyla
required

The voice ID to use.

Available options:
leyla,
zeynep,
alev,
ali,
alper,
mustafa
​
response_format
enum<string>
default:mp3

Response format for the API request.

Available options:
mp3,
opus,
aac,
flac,
wav,
pcm
​
model
enum<string>
default:tts-1

Quality preset. tts-1 is faster; tts-1-hd is higher quality.

Available options:
tts-1,
tts-1-hd

Response

Audio file generated successfully.

Binary WAV audio data.