Quickstart
- Agent Setup
- Build a Conversational App
- Twilio Integration
Libraries & SDKs
API Reference
- WebSocket
- Agents
- Conversations
- Knowledge Base
- Phone Numbers
- Widget
Create Agent
Create an agent from a config object
Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website.
Conversation configuration for an agent
An enumeration.
An enumeration.
An enumeration.
An enumeration.
An enumeration.
An enumeration.
An enumeration.
An enumeration.
Platform settings for the agent are all settings that aren't related to the conversation orchestration and content.
Settings to evaluate an agent's performance. Agents are evaluated against a set of criteria, with success being defined as meeting some combination of those criteria.
An enumeration.
An enumeration.
An enumeration.
Safety object that has the information of safety evaluations based on used voice.
Safety evaluation of the agent. Prompt and first message is taken into account. The unsafe reason is provided from the evaluation
Safety evaluation of the agent. Prompt and first message is taken into account. The unsafe reason is provided from the evaluation
A name to make the agent easier to find
Headers
Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website.
Body
Conversation configuration for an agent
An enumeration.
gpt-4o-mini
, gpt-4o
, gpt-4
, gpt-4-turbo
, gpt-3.5-turbo
, gemini-1.5-pro
, gemini-1.5-flash
, gemini-1.0-pro
, claude-3-5-sonnet
, claude-3-haiku
, grok-beta
, custom-llm
webhook
Configuration for a webhook that will be called by an LLM tool.
An enumeration.
high
An enumeration.
elevenlabs
An enumeration.
pcm_16000
, pcm_22050
, pcm_24000
, pcm_44100
, ulaw_8000
An enumeration.
eleven_turbo_v2
, eleven_turbo_v2_5
An enumeration.
pcm_16000
, pcm_22050
, pcm_24000
, pcm_44100
, ulaw_8000
An enumeration.
0
, 1
, 2
, 3
, 4
conversation_initiation_metadata
, asr_initiation_metadata
, ping
, audio
, interruption
, user_transcript
, agent_response
, agent_response_correction
, client_tool_call
, internal_vad_score
, internal_turn_probability
, internal_tentative_agent_response
Platform settings for the agent are all settings that aren't related to the conversation orchestration and content.
Settings to evaluate an agent's performance. Agents are evaluated against a set of criteria, with success being defined as meeting some combination of those criteria.
An enumeration.
compact
, full
, expandable
An enumeration.
none
, during
, end
Safety object that has the information of safety evaluations based on used voice.
Safety evaluation of the agent. Prompt and first message is taken into account. The unsafe reason is provided from the evaluation
sexual_minors
, forget_moderation
, extremism
, scam_fraud
, political
, self_harm
, illegal_distribution_medical
, sexual_adults
, unknown
Safety evaluation of the agent. Prompt and first message is taken into account. The unsafe reason is provided from the evaluation
sexual_minors
, forget_moderation
, extremism
, scam_fraud
, political
, self_harm
, illegal_distribution_medical
, sexual_adults
, unknown
A name to make the agent easier to find
Response
Was this page helpful?