> ## Documentation Index
> Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Speech-to-Text WebSocket parameters

> Reference for query parameters on the Telnyx Speech-to-Text WebSocket endpoint, including engine, model, language, and redaction options.

All parameters are passed as query string values on the WebSocket URL. Locked at connection time — cannot be changed mid-session.

<ParamField query="transcription_engine" type="string" default="Deepgram">
  `Deepgram`, `Telnyx`, `Google`, `Azure`, `xAI`, `AssemblyAI`, `Speechmatics`, `Soniox`
</ParamField>

<ParamField query="model" type="string" default="per engine">
  See [Engines & Models](/docs/voice/stt/websocket-streaming/parameters/engines-and-models)
</ParamField>

<ParamField query="input_format" type="string" default="mp3">
  See [Audio Formats](/docs/voice/stt/websocket-streaming/parameters/audio-formats)
</ParamField>

<ParamField query="sample_rate" type="integer" default="16000">
  Hz. Required for raw encodings (`linear16`, `mulaw`, `alaw`). Ignored for container formats. Invalid value returns [error 40005](/docs/voice/stt/websocket-streaming/errors).
</ParamField>

<ParamField query="language" type="string" default="en-US">
  Language code or auto-detect behavior varies by engine. See [Language](/docs/voice/stt/websocket-streaming/parameters/language) for details.
</ParamField>

<ParamField query="interim_results" type="string" default="false">
  `"true"` for partial transcripts. See [Interim Results](/docs/voice/stt/websocket-streaming/parameters/interim-results) for details.
</ParamField>

<ParamField query="endpointing" type="string" default="100">
  Silence detection in ms for engines that support endpointing. `"false"` to disable. See [Endpointing](/docs/voice/stt/websocket-streaming/parameters/endpointing) for details.
</ParamField>

<ParamField query="redact" type="string">
  PII redaction. Deepgram only. See [Redaction](/docs/voice/stt/websocket-streaming/parameters/redaction) for details.
</ParamField>

<ParamField query="keyterm" type="string">
  Comma-separated boost terms. Deepgram Nova-3/Flux. See [Keyword Boosting](/docs/voice/stt/websocket-streaming/parameters/keyword-boosting) for details.
</ParamField>

<ParamField query="keywords" type="string">
  Legacy keyword boosting with intensifiers. Deepgram Nova. See [Keyword Boosting](/docs/voice/stt/websocket-streaming/parameters/keyword-boosting) for details.
</ParamField>

<ParamField query="region" type="string" default="eastus">
  Azure Speech Services region.
</ParamField>

<ParamField query="eot_threshold" type="float" default="0.7">
  Flux only. Confidence threshold for `EndOfTurn` events. See [End-of-Turn Detection](/docs/voice/stt/websocket-streaming/parameters/end-of-turn) for details.
</ParamField>

<ParamField query="eot_timeout_ms" type="integer" default="5000">
  Flux only. Max silence before forcing `EndOfTurn`. See [End-of-Turn Detection](/docs/voice/stt/websocket-streaming/parameters/end-of-turn) for details.
</ParamField>

<ParamField query="eager_eot_threshold" type="float">
  Flux only. Speculative `EagerEndOfTurn` threshold. Disabled by default. See [End-of-Turn Detection](/docs/voice/stt/websocket-streaming/parameters/end-of-turn) for details.
</ParamField>

## Example

```
wss://api.telnyx.com/v2/speech-to-text/transcription?transcription_engine=Deepgram&model=nova-3&input_format=wav&language=en-US&interim_results=true
```