Skip to main content

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.

All parameters are passed as query string values on the WebSocket URL. Locked at connection time — cannot be changed mid-session.
​
transcription_engine
string
default:"Deepgram"
Deepgram, Telnyx, Google, Azure, xAI, AssemblyAI
​
model
string
default:"per engine"
See Engines & Models
​
input_format
string
default:"mp3"
See Audio Formats
​
sample_rate
integer
default:"16000"
Hz. Required for raw encodings (linear16, mulaw, alaw). Ignored for container formats. Invalid value returns error 40005.
​
language
string
default:"en-US"
Language code or auto-detect behavior varies by engine. See Language for details.
​
interim_results
string
default:"false"
"true" for partial transcripts. See Interim Results for details.
​
endpointing
string
default:"100"
Silence detection in ms for engines that support endpointing. "false" to disable. See Endpointing for details.
​
redact
string
PII redaction. Deepgram only. See Redaction for details.
​
keyterm
string
Comma-separated boost terms. Deepgram Nova-3/Flux. See Keyword Boosting for details.
​
keywords
string
Legacy keyword boosting with intensifiers. Deepgram Nova. See Keyword Boosting for details.
​
region
string
default:"eastus"
Azure Speech Services region.
​
eot_threshold
float
default:"0.7"
Flux only. Confidence threshold for EndOfTurn events. See End-of-Turn Detection for details.
​
eot_timeout_ms
integer
default:"5000"
Flux only. Max silence before forcing EndOfTurn. See End-of-Turn Detection for details.
​
eager_eot_threshold
float
Flux only. Speculative EagerEndOfTurn threshold. Disabled by default. See End-of-Turn Detection for details.

​
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