Messages
{
"audio": {
"data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAEAfAAABAAgAZGF0YQAAAAA=",
"sample_rate": 16000,
"encoding": "wav"
}
}{
"type": "flush"
}{
"type": "data",
"data": {
"transcript": "నమస్తే ఇది తెలుగు పరీక్ష"
}
}{
"type": "events",
"data": {
"signal_type": "END_SPEECH",
"occured_at": "2026-05-18T12:50:56.000Z"
}
}{
"type": "error",
"data": {
"message": "Invalid audio payload"
}
}Sarvam AI
Saaras v3
“Stream real-time speech-to-text transcripts from Sarvam AI Saaras v3 over WebSocket with voice activity detection across 23 Indian languages. Session configuration is provided via query parameters on the WebSocket upgrade URL: language-code, mode, sample_rate, input_audio_codec, high_vad_sensitivity, vad_signals.”
WSS
/
v1
/
stt
/
sarvam
/
saaras:v3
Messages
{
"audio": {
"data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAEAfAAABAAgAZGF0YQAAAAA=",
"sample_rate": 16000,
"encoding": "wav"
}
}{
"type": "flush"
}{
"type": "data",
"data": {
"transcript": "నమస్తే ఇది తెలుగు పరీక్ష"
}
}{
"type": "events",
"data": {
"signal_type": "END_SPEECH",
"occured_at": "2026-05-18T12:50:56.000Z"
}
}{
"type": "error",
"data": {
"message": "Invalid audio payload"
}
}bearer
type:http
API key issued by SLNG. Pass as Authorization: Bearer <token> in the WebSocket upgrade request headers.
method
type:string
GET
Audio Frame
type:object
Stream a base64-encoded audio chunk to Saaras v3 as a JSON message.
Flush Signal
type:object
Force-finalize buffered audio without closing the connection.
Transcript
type:object
Saaras v3 final transcript chunk for the most recent utterance.
VAD Event
type:object
Voice activity detection signal from Saaras v3.
Error
type:object
Error from Saaras v3 or the SLNG gateway.