Soniox

Soniox specializes in high-accuracy, low-latency multilingual speech recognition. Its multi-language model can handle code-switching scenarios where speakers mix languages within a single conversation — without requiring language pre-selection. A great fit for global or multilingual voice AI applications.
Usage
To use Soniox as the STT engine, pass the following JSON in the STTConfig field of the StartAIConversation API:
// json — STTConfig
{
  "Language": "en",
  "VadSilenceTime": 1000,
  "CustomParam": "{\"STTType\":\"soniox\",\"ApiKey\":\"<your_soniox_api_key>\",\"Model\":\"stt-rt-v4\",\"LanguageHints\":[],\"Context\":{}}"
}
For the complete STTConfig parameter reference, see the STTConfig configuration guide.
Parameter reference
STTConfig fields
The following fields are part of STTConfig. For the full definition, see STTConfig.
Field
Type
Required
Description
Language
String
No
Language code. See Soniox language support.
VadSilenceTime
Integer
No
VAD silence duration (ms). See STTConfig.
CustomParam fields
CustomParam is not part of the standard STTConfig fields. It is only required when using a third-party STT engine, and is used to pass the service provider's authentication parameters.
Field
Type
Required
Description
STTType
String
Yes
Fixed value: "soniox".
ApiKey
String
Yes
Your Soniox API key from the Soniox Console.
Model
String
Yes
Soniox model to use, e.g. "stt-rt-v4". See Soniox Models.
LanguageHints
List
No
Optional list of language codes to prioritize. If omitted or empty, Soniox auto-detects the language. See Supported Languages.
Context
Object
No
Optional context object for domain-specific customization (terms, phrases, etc.). See Soniox Context.
For more details on Soniox, see the Soniox documentation.
Next step: Configure your LLM provider﻿

Field	Type	Required	Description
`Language`	String	No	Language code. See Soniox language support.
`VadSilenceTime`	Integer	No	VAD silence duration (ms). See STTConfig.