For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
An agent represents an AI persona (Support Bot, Sales Agent, etc.)
that can have phone numbers attached to it.
voiceMode: “webhook” (default) forwards transcripts to your webhook.
“hosted” uses a built-in LLM with systemPrompt (no webhook needed).
Authentication
AuthorizationBearer
Bearer authentication of the form Bearer <token>, where token is your auth token.
Request
This endpoint expects an object.
namestringRequired
descriptionstring or nullOptional
voiceModeenumOptional
Allowed values:
enableMessagingboolean or nullOptional
When true, hosted-mode agents can send and read SMS/iMessage during calls. Defaults to true.
modelTierenumOptional
Allowed values:
systemPromptstring or nullOptional
beginMessagestring or nullOptional
voicestring or nullOptional
transferNumberstring or nullOptional
voicemailMessagestring or nullOptional
sttModeenumOptional
Speech-to-text mode. ‘fast’ optimizes for latency, ‘accurate’ optimizes for transcription accuracy (~200ms additional latency).
Allowed values:
ambientSoundenumOptional
Background ambience to mask synthetic silence between turns. ‘none’ disables; ‘office’, ‘coffee-shop’, ‘outdoor’ enable a quiet bed.
Allowed values:
denoisingModeenumOptional
Audio denoising. ‘noise-cancellation’ (default) handles general noise. ‘noise-and-background-speech-cancellation’ is more aggressive for callers in cars, cafes, or near TVs ($0.005/min surcharge).
Allowed values:
maxSilenceMsinteger or nullOptional10000-3600000
Hang up the call after this many milliseconds of caller silence. Default 600000 (10 min). Raise for IVR/hold-music workflows; lower to fail fast on dead lines. Range 10000 (10s) to 3600000 (1 hour).
voiceSpeeddouble or nullOptional0.5-2
Voice speed multiplier. 1.0 is normal pace; lower values slow speech (0.5 is half speed), higher values speed it up (2.0 is double). Range 0.5 to 2.0.
interruptionSensitivitydouble or nullOptional0-1
How easily callers can interrupt the agent. 0 means the agent is never interrupted, 1 means the agent stops at the first sound. Default 0.8. Range 0.0 to 1.0.
enableBackchannelboolean or nullOptional
When true, the agent interjects short filler words like ‘uh-huh’ or ‘mhmm’ during longer caller utterances. Set false to keep the agent silent while the caller is speaking. Defaults to true.
languageenumOptional
BCP-47 locale that drives the agent’s speech recognition and pronunciation. Defaults to ‘en-US’. See the enum for the full set of supported codes.
Response
Successful Response
idstring
namestring
descriptionstring or null
voiceModeenum
Allowed values:
voicestring
createdAtdatetime
enableMessagingbooleanDefaults to true
modelTierenumDefaults to balanced
Allowed values:
systemPromptstring or null
beginMessagestring or null
transferNumberstring or null
voicemailMessagestring or null
sttModeenumDefaults to fast
Speech-to-text mode. ‘fast’ optimizes for latency, ‘accurate’ optimizes for transcription accuracy (~200ms additional latency).
Allowed values:
ambientSoundenumDefaults to none
Background ambience to mask synthetic silence between turns. ‘none’ disables; ‘office’, ‘coffee-shop’, ‘outdoor’ enable a quiet bed.
Allowed values:
denoisingModeenumDefaults to noise-cancellation
Audio denoising. ‘noise-cancellation’ (default) handles general noise. ‘noise-and-background-speech-cancellation’ is more aggressive for callers in cars, cafes, or near TVs ($0.005/min surcharge).
Allowed values:
maxSilenceMsintegerDefaults to 600000
Hang up the call after this many milliseconds of caller silence. Range 10000 (10s) to 3600000 (1 hour). Default 600000 (10 min).
voiceSpeeddoubleDefaults to 1
Voice speed multiplier. Range 0.5 to 2.0. Default 1.0.
interruptionSensitivitydoubleDefaults to 0.8
How easily callers can interrupt the agent. Range 0.0 to 1.0. Default 0.8.
enableBackchannelbooleanDefaults to true
When true, the agent interjects short filler words like ‘uh-huh’ or ‘mhmm’ during longer caller utterances. Defaults to true.
languagestringDefaults to en-US
BCP-47 locale that drives the agent’s speech recognition and pronunciation. Defaults to ‘en-US’.