Build your agent

Sarvam

Built for Indian languages. Every listening setting for Sarvam, and how to set it.

Service: sarvam. A new setup starts from:

1{
2  "service": "sarvam",
3  "model": "saaras:v3",
4  "language": "hi-IN",
5  "mode": "transcribe"
6}

Set it

On the flow's Voice tab, choose Listening, then Sarvam. Or from code:

1await voxio.flows.update(flowKey, {
2  stt: {"service":"sarvam","model":"saaras:v3","language":"hi-IN","mode":"transcribe"},
3});

Settings marked “under More settings” are behind More settings in the dashboard.

modelstring: Model. Which speech model listens. Hover an option to compare. Default: "saaras:v3".
languagestring: Language. The language callers speak, or detect it. Default: "hi-IN".
modestring: Output. How the transcript is written. Default: "transcribe".
keytermstring[]: Boost words (under More settings). Words the agent should never mishear.
vad-signalsboolean: Speech-start events (under More settings). Signal the moment the caller starts speaking. Default: true.
high-vad-sensitivityboolean: Hear quiet speakers (under More settings). Pick up soft voices; may also pick up background noise. Default: false.
positive-speech-thresholdnumber: Speech threshold (under More settings). How confident it must be that someone is speaking. From 0 to 1. Default: 0.7.
negative-speech-thresholdnumber: Silence threshold (under More settings). How confident it must be that speech has stopped. From 0 to 1. Default: 0.45.

Value	Name	Notes
`saaras:v4`	Saaras v4	Latest. Newest Sarvam model, better across Indian languages.
`saaras:v3`	Saaras v3	Reliable for Hindi and English calls.