Update Assistant
Update Assistant
Update the configuration of an existing AI assistant
PUT
Update Assistant
This endpoint allows you to update the configuration of an existing AI assistant. All fields are optional – only the fields provided will be updated. For detailed field descriptions and options, see Create Assistant.
Path Parameter
The unique identifier of the assistant to be updated
Request Body
Core Fields
The name of the assistant (max. 255 characters)
The voice ID to be used for the assistant. Use the Get Voices endpoint with the
mode parameter to get voices compatible with your engine mode.The language ID for the assistant. Use the Get Languages endpoint to retrieve available languages.
The assistant type. Options:
inbound, outboundThe engine mode. Options:
pipeline, multimodal, dualplexThe timezone for the assistant (e.g., “Europe/Berlin”, “America/New_York”)
The initial message the assistant will speak at call start (max. 200 characters)
The system prompt defining the assistant’s behaviour and personality
Mode-Specific Fields
The LLM model ID to use. Only applicable in
pipeline mode.Use the Get Models endpoint to retrieve available models.The multimodal model ID. Applicable only in
multimodal and dualplex modes.Use the Get Models endpoint to retrieve available multimodal models.Fallback LLM model ID for tool calls in multimodal/dualplex modes. Set to
null to remove.Sensitivity of speaker turn detection for multimodal/dualplex modes (0-1). Set to
null for automatic.Secondary Languages
Array of additional language IDs the assistant can speak. Replaces existing secondary languages. Pass an empty array
[] to remove all secondary languages.Knowledgebase Settings
The ID of the knowledgebase to link. Set to
null to remove.How the knowledgebase should be used. Options:
function_call- AI uses a function to search (required for multimodal/dualplex)prompt- knowledge is injected into the prompt (pipeline only)
Phone Number
The ID of a phone number to assign. Set to
null to unassign. Must belong to your account.Custom Mid-Call Tools
Array of custom mid-call tool IDs to synchronize. Replaces all existing tool assignments. Pass an empty array
[] to remove all tools. Each tool must belong to your account.Built-in Tools
Array of built-in tools. Replaces all existing built-in tools. Pass an empty array
[] to remove all tools.When you list assistants, each configured tool is returned as
{ "type": "...", "data": { ... } } with the same field names nested under data (not top-level).Speech and TTS Settings
Whether emotional text-to-speech synthesis is enabled
Voice stability setting (0-1). Higher = more consistent voice
Voice similarity setting (0-1). Higher = closer to original voice
Speech speed multiplier (0.7-1.2)
LLM temperature setting (0-1). Lower = more deterministic
Custom TTS provider ID. Set to
null to use the system default voice. See Get Synthesizer Providers.Custom STT provider ID. Pipeline mode only. Set to
null to use the system default voice. See Get Transcriber Providers.Call Behavior Settings
Whether caller interruptions are allowed.
Whether filler audio should be used during processing.
Custom filler profiles per category. Replaces the existing filler configuration. Each category is an array of short phrases.
positive: Fillers for affirmative responsesnegative: Fillers for negative/neutral responsesquestion: Fillers when processing a questionneutral: Fillers for neutral confirmations
Whether the call should be recorded
Whether noise cancellation should be enabled
If true, the assistant waits for the customer to speak first
Timing Settings
Maximum call duration in seconds (20-1200)
Maximum silence duration before re-engagement in seconds (1-360)
Maximum silence at the start of the call before termination (1-120 seconds). Set to
null to disable.Maximum ringing time before aborting (1-60 seconds)
Re-Engagement Settings
Interval for re-engagement in seconds (7-600)
Custom prompt for re-engagement messages (max. 1000 characters). Set to
null to use the default.Voicemail Settings
Whether to end the call when voicemail is detected
Message to leave on voicemail before hanging up (max. 1000 characters). Set to
null to disable.Endpoint Detection
Type of voice activity detection. Options:
vad, aiEndpoint sensitivity level (0-5)
Interruption sensitivity level (0-5)
Minimum number of words before interruption is allowed (0-10). Set to
null to disable.Ambient Sound
Background ambient sound. Options:
off, office, city, forest, crowded_room, cafe, natureVolume of the ambient sound (0-1)
Webhook Configuration
Whether webhook notifications are enabled
The webhook URL for post-call notifications. Set to
null to remove.Whether webhooks should be sent only for successfully completed calls (not on failed/no-answer)
Whether the recording URL should be included in the webhook payload
Post-Call Evaluation
Whether AI-based post-call evaluation is enabled
Schema definition for extracting post-call data. Replaces the existing schema.
Variables
Key-value pairs for custom variables. Replaces all existing variables.
Example Requests
Update Basic Settings
Switch to Multimodal Mode
Update Tools and Knowledgebase
Update Re-Engagement and Voicemail
Remove Optional Settings
Response
Success message confirming the assistant update
Notes
- Only the fields you provide in the request body will be updated
- To remove optional fields, explicitly set them to
null - To clear arrays (tools, secondary languages), pass an empty array
[] - The assistant must belong to the authenticated user
- Use the Get Voices endpoint with the
modeparameter to get compatible voices - For multimodal/dualplex modes,
knowledgebase_modemust be set tofunction_call - In multimodal/dualplex modes, interruptions (
allow_interruptions) cannot be disabled - Changing mode resets mode-specific settings (LLM model, multimodal model, providers)

