Create Agent
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The initial message that the agent will say. If null, the agent will wait for the user to speak first.
The prompt of the agent.
The voice provider.
The credential id to use for the provider. If null, we include the provider cost in the conversation.
The playht model to use.
Control how fast the generated audio should be. A number greater than 0 and less than or equal to 5.0
A floating point number between 0, inclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used.
A number between 1 and 2. This number influences how closely the generated speech adheres to the input text.
A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance.
The language model provider.
The credential id to use for the provider. If null, we include the provider cost in the conversation.
The OpenAI language model to use.
The list of OpenAI tools.
The temperature of the model. Default is 0 for optimized caching performance.
The maximum number of tokens to generate for an each response from the agent. Default is 300.
The transcriber provider.
The credential id to use for the provider. If null, we include the provider cost in the conversation.
The deepgram model to use.
The selected language for the transcription.
Specific keywords you want to detect in the transcription. This is useful to correctly understand product or company names.
The maximum conversation duration in seconds. If null, the conversation can be of any duration. The default value is 10 min.
The webhooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
The hooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
The metadata of the agent. This is used to store additional information about the agent.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
The initial message that the agent will say. If null, the agent will wait for the user to speak first.
The prompt of the agent.
The voice provider.
playht The credential id to use for the provider. If null, we include the provider cost in the conversation.
The playht model to use.
susan, william, phoebe, arthur, ayla, dylan, madelyn, oliver, sophia Control how fast the generated audio should be. A number greater than 0 and less than or equal to 5.0
0 < x < 5A floating point number between 0, inclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used.
0 < x < 2A number between 1 and 2. This number influences how closely the generated speech adheres to the input text.
1 < x < 2A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance.
1 < x < 30The language model provider.
openai The credential id to use for the provider. If null, we include the provider cost in the conversation.
The OpenAI language model to use.
gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo-16k, gpt-3.5-turbo-0613, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-turbo-preview, gpt-4-0125-preview, gpt-4-1106-preview, gpt-4-0613, gpt-4, gpt-4o The list of OpenAI tools.
This is the type of OpenAI Tool.
function The function definition to be called.
This is the name of the function to be called. Must be less than 64 characters (a-z, A-Z, 0-9, including underscores).
The description of the OpenAI function call.
The parameters of the OpenAI function call.
This provides a description of the properties required by the function.
This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties.
object This specifies the properties that are required by the function.
The temperature of the model. Default is 0 for optimized caching performance.
0 < x < 2The maximum number of tokens to generate for an each response from the agent. Default is 300.
The transcriber provider.
deepgram The credential id to use for the provider. If null, we include the provider cost in the conversation.
The deepgram model to use.
nova-2, nova-2-general, nova-2-meeting, nova-2-phonecall, nova-2-finance, nova-2-voicemail, nova-2-medical, nova-2-drivethru, nova-2-automotive, nova-2-conversationalai The selected language for the transcription.
en, fr, es, de, it, nl, pt, ru, ja, cs, da, el, hi, id, ko, no, pl, sv, tr, uk Specific keywords you want to detect in the transcription. This is useful to correctly understand product or company names.
The maximum conversation duration in seconds. If null, the conversation can be of any duration. The default value is 10 min.
The webhooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
phone_call:connection_requested, phone_call:rejected, phone_call:accepted, function_call:triggered, conversation:started, conversation:ended, conversation:duration, speech:started, speech:ended, message:sent, message:generated The url of the webhook. Where the requests will be sent.
The method of the webhook.
GET, POST The hooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
phone_call:connection_requested, phone_call:rejected, phone_call:accepted, function_call:triggered, conversation:started, conversation:ended, conversation:duration, speech:started, speech:ended, message:sent, message:generated Response
The uri of the agent.
The id of the owner of the agent.
The date and time the agent was created.
The date and time the agent was last updated.
The id of the agent.
The initial message that the agent will say. If null, the agent will wait for the user to speak first.
The prompt of the agent.
The voice provider.
playht The credential id to use for the provider. If null, we include the provider cost in the conversation.
The playht model to use.
susan, william, phoebe, arthur, ayla, dylan, madelyn, oliver, sophia Control how fast the generated audio should be. A number greater than 0 and less than or equal to 5.0
0 < x < 5A floating point number between 0, inclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used.
0 < x < 2A number between 1 and 2. This number influences how closely the generated speech adheres to the input text.
1 < x < 2A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance.
1 < x < 30The language model provider.
openai The credential id to use for the provider. If null, we include the provider cost in the conversation.
The OpenAI language model to use.
gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo-16k, gpt-3.5-turbo-0613, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-turbo-preview, gpt-4-0125-preview, gpt-4-1106-preview, gpt-4-0613, gpt-4, gpt-4o The list of OpenAI tools.
This is the type of OpenAI Tool.
function The function definition to be called.
This is the name of the function to be called. Must be less than 64 characters (a-z, A-Z, 0-9, including underscores).
The description of the OpenAI function call.
The parameters of the OpenAI function call.
This provides a description of the properties required by the function.
This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties.
object This specifies the properties that are required by the function.
The temperature of the model. Default is 0 for optimized caching performance.
0 < x < 2The maximum number of tokens to generate for an each response from the agent. Default is 300.
The transcriber provider.
deepgram The credential id to use for the provider. If null, we include the provider cost in the conversation.
The deepgram model to use.
nova-2, nova-2-general, nova-2-meeting, nova-2-phonecall, nova-2-finance, nova-2-voicemail, nova-2-medical, nova-2-drivethru, nova-2-automotive, nova-2-conversationalai The selected language for the transcription.
en, fr, es, de, it, nl, pt, ru, ja, cs, da, el, hi, id, ko, no, pl, sv, tr, uk Specific keywords you want to detect in the transcription. This is useful to correctly understand product or company names.
The maximum conversation duration in seconds. If null, the conversation can be of any duration. The default value is 10 min.
The webhooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
phone_call:connection_requested, phone_call:rejected, phone_call:accepted, function_call:triggered, conversation:started, conversation:ended, conversation:duration, speech:started, speech:ended, message:sent, message:generated The url of the webhook. Where the requests will be sent.
The method of the webhook.
GET, POST The hooks of the agent. These are used for real-time conversation events such as function_calls, messages and much more.
phone_call:connection_requested, phone_call:rejected, phone_call:accepted, function_call:triggered, conversation:started, conversation:ended, conversation:duration, speech:started, speech:ended, message:sent, message:generated