Create Agent
Create a new agent.
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
Bearer authentication of the form Bearer <token>, where token is your auth token.
Headers
Target a sub-account. Pass a sub-account ID to scope this request. Omit to use the master account.
Request
When true, hosted-mode agents can send and read SMS/iMessage during calls. Defaults to true.
Hosted-mode only. User-defined function tools the agent can call during a call (look up a record, save call notes, etc.). Each points at your HTTPS endpoint; the voice provider invokes it and feeds the JSON response back to the agent. Ignored in webhook mode. Maximum 20 tools.
Speech-to-text mode. ‘fast’ optimizes for latency, ‘accurate’ optimizes for transcription accuracy (~200ms additional latency).
Background ambience to mask synthetic silence between turns. ‘none’ disables; ‘office’, ‘coffee-shop’, ‘outdoor’ enable a quiet bed.
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).
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).
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.
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.
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
Speech-to-text mode. ‘fast’ optimizes for latency, ‘accurate’ optimizes for transcription accuracy (~200ms additional latency).
Background ambience to mask synthetic silence between turns. ‘none’ disables; ‘office’, ‘coffee-shop’, ‘outdoor’ enable a quiet bed.
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).
Hang up the call after this many milliseconds of caller silence. Range 10000 (10s) to 3600000 (1 hour). Default 600000 (10 min).
When true, the agent interjects short filler words like ‘uh-huh’ or ‘mhmm’ during longer caller utterances. Defaults to true.
BCP-47 locale that drives the agent’s speech recognition and pronunciation. Defaults to ‘en-US’.