Skip to main content
POST
/
v1
/
tts
/
soniox
/
tts-rt:v1
Soniox TTS v1
curl --request POST \
  --url https://api.slng.ai/v1/tts/soniox/tts-rt:v1 \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "Hello from Soniox text-to-speech.",
  "voice": "Adrian",
  "audio_format": "wav",
  "sample_rate": 24000
}
'
{
  "error": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.slng.ai/llms.txt

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

Authorizations

​
Authorization
string
header
required

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

Headers

​
x-region
enum<string>

Override the default region for this request.

Available options:
na

Body

application/json

Soniox real-time TTS synthesis request.

​
text
string
required

Text to synthesize.

Required string length: 1 - 5000
​
voice
string
default:Adrian

Voice name.

​
language
string
default:en

ISO language code.

​
audio_format
enum<string>
default:wav

Output audio format.

Available options:
wav,
mp3,
pcm_s16le,
pcm_s16be
​
sample_rate
integer
default:24000

Output sample rate in Hz.

​
bitrate
integer

Codec bitrate in bps. Only applicable to lossy compressed formats.

​
model
string
default:tts-rt-v1

Soniox TTS model identifier.

Response

Success