Feedback

Tencent

Tencent's in-house STT engine is natively integrated into the TRTC platform, delivering ultra-low latency through direct access to TRTC's real-time audio pipeline. Advanced audio processing — including AI noise suppression, echo cancellation, and customizable conversation modes — ensures clear transcription even in noisy environments. The flexible engine framework supports a broad range of models covering Chinese, English, and many other languages, all configurable through STTConfig fields with no additional service accounts required. Ideal for teams seeking the fastest integration path with zero external dependencies.
Usage
To use Tencent STT as the STT engine, pass the following JSON in the STTConfig field of the StartAIConversation API:
// json — STTConfig
{
  "Language": "zh",
  "VadSilenceTime": 1000
}
For the complete Tencent STT parameter reference, see the STT parameter configuration guide.
Built-in provider:
Tencent STT is TRTC's built-in speech recognition engine. Unlike third-party providers (Azure, Deepgram, Soniox), it does not require the CustomParam field — just configure the STTConfig top-level fields below.
Parameter reference
The following fields are part of STTConfig. For the full definition, see STTConfig.
Field
Type
Required
Description
Language
String
No
Primary language code for recognition. 
Possible Value：
Chinese ("zh")
English ("en")
Cantonese ("yue")
Arabic ("ar")
German ("de")
French ("fr")
Spanish ("es")
Portuguese ("pt")
Indonesian ("id")
Italian ("it")
Korean ("ko")
Russian ("ru")
Thai ("th")
Vietnamese ("vi")
Japanese ("ja")
Turkish ("tr")
Hindi ("hi")
Malay ("ms")
Dutch ("nl")
Swedish ("sv")
Danish ("da")
Finnish ("fi")
Polish ("pl")
Czech ("cs")
Filipino ("fil")
Persian ("fa")
Greek ("el")
Hungarian ("hu")
See more STTConfig.
VadSilenceTime
Integer
No
VAD silence duration in milliseconds. When silence exceeds this value, the current speech segment ends. See STTConfig.
Next step: Configure your LLM provider﻿

Field	Type	Required	Description
`Language`	String	No	Primary language code for recognition. Possible Value： `Chinese ("zh")` `English ("en")` `Cantonese ("yue")` `Arabic ("ar")` `German ("de")` `French ("fr")` `Spanish ("es")` `Portuguese ("pt")` `Indonesian ("id")` `Italian ("it")` `Korean ("ko")` `Russian ("ru")` `Thai ("th")` `Vietnamese ("vi")` `Japanese ("ja")` `Turkish ("tr")` `Hindi ("hi")` `Malay ("ms")` `Dutch ("nl")` `Swedish ("sv")` `Danish ("da")` `Finnish ("fi")` `Polish ("pl")` `Czech ("cs")` `Filipino ("fil")` `Persian ("fa")` `Greek ("el")` `Hungarian ("hu")` See more STTConfig.
`VadSilenceTime`	Integer	No	VAD silence duration in milliseconds. When silence exceeds this value, the current speech segment ends. See STTConfig.