SLNG// hosted
3rd Party
{
"type": "init",
"model": "eleven-flash:2.5",
"voice": "astra",
"config": {
"sample_rate": 24000,
"encoding": "mp3"
}
}{
"type": "text",
"text": "Hello, this is a test of text-to-speech synthesis."
}{
"type": "flush"
}{
"type": "clear"
}{
"type": "close"
}"0000FF00000000FF00000000010101010101010100000000FFFFFFFFFFFEFEFDFEFEFEFEFDFDFEFEFEFEFEFEFEFEFEFFFFFFFFFEFEFEFEFF0001000001020303030303030303030201010000FFFFFEFDFDFDFDFEFFFFFFFF0001020303020201000000FFFDFCFBFAFAFBFAF9F8F7F7F7F6F6F4F2F2F3F7FC000406090F14191A19181715110E0A05FEF9F6F3F0EEECEBEBECEEF2F6F9FC0005090D0F101010100E0C080401"{
"type": "flushed"
}{
"type": "cleared"
}{
"type": "error",
"code": "provider_error",
"message": "Provider returned an unexpected error"
}Aura 2
Text-to-Speech API for generating speech from text using Deepgram aura. Real-time conversational TTS designed for voice agents with ultra-low latency. Establishes a WebSocket connection for real-time text-to-speech. Audio data is sent as raw binary WebSocket frames (not JSON audio_chunk messages).
{
"type": "init",
"model": "eleven-flash:2.5",
"voice": "astra",
"config": {
"sample_rate": 24000,
"encoding": "mp3"
}
}{
"type": "text",
"text": "Hello, this is a test of text-to-speech synthesis."
}{
"type": "flush"
}{
"type": "clear"
}{
"type": "close"
}"0000FF00000000FF00000000010101010101010100000000FFFFFFFFFFFEFEFDFEFEFEFEFDFDFEFEFEFEFEFEFEFEFEFFFFFFFFFEFEFEFEFF0001000001020303030303030303030201010000FFFFFEFDFDFDFDFEFFFFFFFF0001020303020201000000FFFDFCFBFAFAFBFAF9F8F7F7F7F6F6F4F2F2F3F7FC000406090F14191A19181715110E0A05FEF9F6F3F0EEECEBEBECEEF2F6F9FC0005090D0F101010100E0C080401"{
"type": "flushed"
}{
"type": "cleared"
}{
"type": "error",
"code": "provider_error",
"message": "Provider returned an unexpected error"
}API key issued by SLNG. Pass as Authorization: Bearer <token> in the WebSocket upgrade request headers.
GET
Target world part override. Auto-selected if not provided. Available world parts: na, eu.
na, euInitialize a TTS session with model and voice configuration.
Send text to synthesize into audio output.
Force any buffered text/audio to be finalized and delivered.
Clear any queued text/audio from the current session.
Close the session and stop any further audio.
Raw binary audio frame from Deepgram Aura.
Acknowledges that buffered output was flushed.
Acknowledges that queued output was cleared.
Indicates an error occurred during synthesis.
Was this page helpful?