Soniox

Service: soniox. A new setup starts from:

1{
2  "service": "soniox",
3  "model": "stt-rt-v4",
4  "language": [
5    "hi",
6    "en"
7  ]
8}

#Set it

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

1await voxio.flows.update(flowKey, {
2  stt: {"service":"soniox","model":"stt-rt-v4","language":["hi","en"]},
3});

#Settings

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

modelstring

Model. Which speech model listens. Hover an option to compare. Default: "stt-rt-v4".

languagestring[]

Languages. Languages callers are likely to speak.

language-hints-strictboolean

Only these languages (under More settings). Ignore any language not listed. Default: false.

keytermstring[]

Boost words. Words the agent should never mishear.

context-textstring

Context (under More settings). Background that helps recognition.

enable-endpoint-detectionboolean

Detect end of speech (under More settings). Let the model decide when a sentence has ended. Default: true.

max-endpoint-delay-msnumber (ms)

Max end-of-speech delay (under More settings). Longest wait for the end of a sentence. From 500 to 3000. Default: 2000.

endpoint-sensitivitynumber

End-of-speech sensitivity (under More settings). Higher ends sentences sooner. From -1 to 1. Default: 0. Only applies to some models.

endpoint-latency-adjustment-levelnumber

Latency adjustment (under More settings). Trade accuracy for speed. 0 is the most accurate. From 0 to 3. Default: 0. Only applies to some models.

enable-speaker-diarizationboolean

Tell speakers apart (under More settings). Label who said what when more than one person talks. Default: false.

enable-language-identificationboolean

Identify language (under More settings). Detect which language each sentence is in. Default: false.

#Choices

#Next steps

• Listening: compare the other providers.
• Turn-taking: when the agent answers.