ai.params
Parameters for AI that can be passed in ai.params
at the top level of the ai
Method.
Name | Type | Default | Description |
---|---|---|---|
params Optional | object | - | An object that accepts the params parameters . |
params Parameters
Name | Type | Default | Description |
---|---|---|---|
acknowledge_interruptions Optional | boolean | string | - | Instructs the agent to acknowledge crosstalk and confirm user input when the user speaks over the agent. |
ai_volume Optional | integer | 0 (the natural volume of the AI) | Adjust the volume of the AI. Allowed values from -50 -50 . |
attention_timeout Optional | integer | 10000 ms (10 seconds) | Amount of time, in ms, to wait before prompting the user to respond. Allowed values from 10,000 -600,000 . Set to 0 to disable. |
attention_timeout_prompt Optional | string | The user has not responded, try to get their attention. Stay in the same language. | A custom prompt that is fed into the AI when the attention_timeout is reached. |
background_file Optional | string | 600000 ms (10 minutes) | URL of audio file to play in the background while AI plays in foreground. |
background_file_loops Optional | integer | undefined (loops indefinitely) | Maximum number of times to loop playing the background file. |
background_file_volume Optional | string | - | Defines background_file volume within a range of -50 to +50 . |
barge_match_string Optional | string | - | Takes a string, including a regular expression, defining barge behavior. For example, this param can direct the AI to stop when the word "hippopotomus" is input. |
barge_min_words Optional | string | - | Defines the number of words that must be input before triggering barge behavior, in a range of 1-99. |
conscience Optional | string | "Remember to stay in character. You must not do anything outside the scope of your provided role." | Sets the prompt which binds the agent to its purpose. |
conversation_id Optional | string | - | Used by check_for_input and save_conversation to identify an individual conversation. |
debug_webhook_level Optional | integer | - | Enables debugging to the set URL. |
debug_webhook_url Optional | string | - | Each interaction between the AI and end user is posted in real time to the established URL. Authentication can also be set in the url in the format of username:password@url . |
direction Optional | string | the natural direction of the call | Forces the direction of the call to the assistant. Valid values are inbound and outbound . |
digit_terminators Optional | string | - | DTMF digit, as a string, to signal the end of input (ex: "#") |
digit_timeout Optional | integer | 3000 ms | Time, in ms, at the end of digit input to detect end of input. Allowed values from 250 -10,000 . |
eleven_labs_stability Optional | number | - | The stability slider determines how stable the voice is and the randomness between each generation. Lowering this slider introduces a broader emotional range for the voice. Important: This will only works when elevenlabs is set in the ai.languages.voice as the engine id. |
eleven_labs_similarity Optional | number | - | The similarity slider dictates how closely the AI should adhere to the original voice when attempting to replicate it. The higher the similarity, the closer the AI will sound to the original voice. Important: This will only works when elevenlabs is set in the ai.languages.voice as the engine id. |
end_of_speech_timeout Optional | integer | 2000 ms (2 seconds) | Amount of silence, in ms, at the end of an utterance to detect end of speech. Allowed values from 250 -10,000 . |
energy_level Optional | number | 52 | Amount of energy necessary for bot to hear you (in dB). Allowed values from 0.0 -100.0 . |
hold_music Optional | string | - | A URL for the hold music to play, accepting WAV, mp3, and FreeSWITCH tone_stream. |
hold_on_process Optional | boolean | - | Enables hold music during SWAIG processing. |
inactivity_timeout Optional | integer | 600000 ms (10 minutes) | Amount of time, in ms, to wait before exiting the app due to inactivity. Allowed values from 10,000 -3,600,000 . |
input_poll_freq Optional | string | - | Check for input function with check_for_input . Example use case: Feeding an inbound SMS to AI on a voice call, eg., for collecting an email address or other complex information. |
interrupt_on_noise Optional | boolean | - | When enabled, barges agent upon any sound interruption longer than 1 second. |
interrupt_prompt Optional | string | - | Provide a prompt for the agent to handle crosstalk. |
languages_enabled Optional | boolean | - | Allows multilingualism when true . |
local_tz Optional | string | GMT | The local timezone setting for the AI. Value should use IANA TZ ID |
outbound_attention_timeout Optional | integer | - | Sets a time duration for the outbound call recipient to respond to the AI agent before timeout, in a range from 10000 to 600000 . |
save_conversation Optional | boolean | false | Send a summary of the conversation after the call ends. This requires a post_url to be set in the ai parameters and the conversation_id defined below. This eliminates the need for a post_prompt in the ai parameters. |
swaig_allow_settings Optional | boolean | - | Allows tweaking any of the indicated settings, such as barge_match_string, using the returned SWML from the SWAIG function. |
swaig_allow_swml Optional | boolean | - | Allows your SWAIG to return SWML to be executed. |
swaig_post_conversation Optional | boolean | - | Post entire conversation to any SWAIG call. |
transfer_summary Optional | boolean | - | Pass a summary of a conversation from one AI agent to another. For example, transfer a call summary between support agents in two departments. |
verbose_logs Optional | boolean | - | Enable verbose logging. |
wait_for_user Optional | boolean | false | When false, AI agent will initialize dialogue after call is setup. When true, agent will wait for the user to speak first. |