API Documentation
Current APIs
- Agent
- Making phone calls
- Executions & calls data
- Phone numbers
- Inbound Agents
- Batches
- Knowledgebases
- Providers
- User
Legacy APIs
Create agent
Creates a new agent
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Configuration of the agent
The name of the agent
Initial welcome message by agent
Webhook URL to receive data for all conversations as get_execution API
Agent type
An array of tasks that the agent can perform
Prompts to be provided to the agent. It can have multiple tasks of the form task_<task_id>
The system prompt fed into the agent
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Configuration of the agent
The name of the agent
An array of tasks that the agent can perform
Type of task
conversation, extraction, summarization, webhook Configuration of multiple tools that form a task
Configuration of LLM model for the agent task
streaming, preprocessed Semantic routing layer
Configuration of Synthesizer model for the agent task
polly, elevenlabs, deepgram, styletts wav Configuration of Transcriber model for the agent task
Identification provider for Deepgram
deepgram nova-2, nova-2-meeting, nova-2-phonecall, nova-2-finance, nova-2-conversationalai, nova-2-medical, nova-2-drivethru, nova-2-automotive en, hi, es, fr linear16 Api tools you'd like the agents to have access to
Description of all the tools you'd like to add to the agent. It needs to be a JSON string as this will be passed to LLM.
Parameters for each tool, where keys must match the name field in the tools array.
Should be used onkly in conversation task for now and it consists of all the required configuration for conversational nuances
Time to wait in seconds before hanging up in case user doesn't speak a thing
Since we work with interim results, this will dictate the linear delay to add before speaking everytime we get a partial transcript from ASR
To avoid accidental interruption, how many words should we wait for before interrupting
Weather to use LLM prompt to hang up or not. Pretty soon this will be replaced by predefined function
This will enable agent to acknowledge when user is speaking long sentences
Gap between every successive acknowledgement. We will also add a random jitter to this value to make it more random
Basic delay after which we should start with backchanneling
Toggle to add ambient noise to the call to add more naturalism
Track for ambient noise can be coffee-shop, call-center, office-ambience
office-ambience, coffee-shop, call-center The call automatically disconnects reaching this limit
Initial welcome message by agent
Webhook URL to receive data for all conversations as get_execution API
Agent type