curl --request GET \
--url https://api.eqho.ai/v1/agents \
--header 'X-API-KEY: <api-key>'{
"agents": [
{
"avatar": "WOMAN",
"data_store_ids": [
"65a9758171f55af646a19890"
],
"description": "An agent that the sales team is testing.",
"greeting_type_inbound": "static",
"greeting_type_outbound": "ai",
"name": "Liz",
"personality": {
"adherence": 0.75,
"empathy": 0.5,
"humor": 0.25
},
"role_ids": [
"65a9758171f55af646a19890"
],
"script_id": "65a9758171f55af646a19890",
"structured_greetings": [
{
"call_type": "inbound",
"greeting_type": "static",
"text": "Hello! Welcome to our service. How can I assist you today?"
},
{
"call_type": "outbound",
"communication_tone": "friendly",
"greeting_length": "short",
"greeting_type": "ai",
"mention_ids": [
"673e488ce7d69488a458cf3e",
"973e488ce7d69488a458cf3e"
]
}
],
"voice_audio_id": "Y94lg6clSowTJ0jJOlyc"
}
],
"meta": {
"per_page": 123,
"last_page": 123,
"current_page": 123,
"next_page": 123,
"prev_page": 123,
"total": 123
}
}Get Agents
curl --request GET \
--url https://api.eqho.ai/v1/agents \
--header 'X-API-KEY: <api-key>'{
"agents": [
{
"avatar": "WOMAN",
"data_store_ids": [
"65a9758171f55af646a19890"
],
"description": "An agent that the sales team is testing.",
"greeting_type_inbound": "static",
"greeting_type_outbound": "ai",
"name": "Liz",
"personality": {
"adherence": 0.75,
"empathy": 0.5,
"humor": 0.25
},
"role_ids": [
"65a9758171f55af646a19890"
],
"script_id": "65a9758171f55af646a19890",
"structured_greetings": [
{
"call_type": "inbound",
"greeting_type": "static",
"text": "Hello! Welcome to our service. How can I assist you today?"
},
{
"call_type": "outbound",
"communication_tone": "friendly",
"greeting_length": "short",
"greeting_type": "ai",
"mention_ids": [
"673e488ce7d69488a458cf3e",
"973e488ce7d69488a458cf3e"
]
}
],
"voice_audio_id": "Y94lg6clSowTJ0jJOlyc"
}
],
"meta": {
"per_page": 123,
"last_page": 123,
"current_page": 123,
"next_page": 123,
"prev_page": 123,
"total": 123
}
}Authorizations
Response
Successful Response
A list of AgentModel instances.
Show child attributes
Show child attributes
Language codes that are supported by Eqho Agents.
multi, bg, ca, cs, da, da-DK, de, de-CH, el, en, en-US, en-AU, en-GB, en-NZ, en-IN, es, et, fi, fr, fr-CA, hi, hu, id, it, ja, lt, lv, no, nl, pl, pt, pt-BR, pt-PT, ro, ru, sk, th, th-TH, tr, uk, vi, zh, zh-CN, zh-TW, zh-HK Deprecated. Use script_ids instead.
Describes the personality of an agent. These values will be injected into the agent's prompt. LLM might use them to adjust the agent's responses.
Show child attributes
Show child attributes
Script adherence parameter, 0 represents freedom to adjust verbiage, and 1 signifies the exact script word for word flow.
0 <= x <= 10 represents a lack of empathy, and 1 signifies a high level of empathy.
0 <= x <= 10 represents no humor, and 1 signifies a high level of humor.
0 <= x <= 1Deprecated. This field is no longer recommended for use and will be removed in future versions. Use greeting_type with value 'none' instead.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
web_voice, telephony, sms, email, chatbot Show child attributes
Show child attributes
system, user, assistant, tool outbound, inbound When enabled, it will append stage sections to the original system prompt instead of overriding it.
When enabled, it will append stage conversation seeder to the original conversation seeder instead of overriding it.
Show child attributes
Show child attributes
web_voice, telephony, sms, email, chatbot Show child attributes
Show child attributes
system, user, assistant, tool outbound, inbound When enabled, it will append stage sections to the original system prompt instead of overriding it.
When enabled, it will append stage conversation seeder to the original conversation seeder instead of overriding it.
Settings for the Agent's LLM model.
Show child attributes
Show child attributes
The ID of the LLM model to use. If None, the Eqho default model will be used.
Number between -2.0 and 2.0. If None, the Eqho default value will be used.
Used to discourage the model from repeating the same words or phrases too frequently within the generated text. A higher frequency_penalty value will result in the model being more conservative in its use of repeated tokens.
Available for OpenAI models only.
The maximum number of tokens the AI can generate.
Number between -2.0 and 2.0. If None, the Eqho default value will be used.
Used to encourage the model to include a diverse range of tokens in the generated text. A higher presence_penalty value will result in the model being more likely to generate tokens that have not yet been included in the generated text.
Available for OpenAI models only.
The sampling temperature, if you use OpenAI model, the temperature should be between 0 and 2 and if you use Anthropic model, the temperature should be between 0 and 1. If None, the Eqho default value will be used. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
none, low, medium, high low, medium, high Show child attributes
Show child attributes
Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability
Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely
Add punctuation and capitalization to the transcript
Convert numbers from written format to numerical format
Keywords can boost or suppress specialized terminology and brands
Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0
Identify and extract key entities from content in submitted audio.
Indicates how long Deepgram will wait to detect whether a speaker has finished speaking or pauses for a significant period of time. When set to a value, the streaming endpoint immediately finalizes the transcription for the processed time range and returns the transcript with a speech_final parameter set to true. Can also be set to false to disable endpointing
Filler Words can help transcribe interruptions in your audio, like 'uh' and 'um'
Show child attributes
Show child attributes
Time in seconds to wait before sending greeting message for outbound calls.
Time in seconds to wait before sending greeting message for inbound calls.
static, ai, none static, ai, none Show child attributes
Show child attributes
The type of call this greeting is for
outbound, inbound The default static greeting text to be used if the user does not provide a greeting text per conversation medium
The static greetings for all conversation mediums
Show child attributes
Show child attributes
This will allow us to have multiple types of greetings, to have some disabled, some enabled and allow the user to A/B test different greeting settings
static, ai, none The communication tone for this greeting
friend, business_casual, business_professional, formal The desired length of this greeting
short, medium, long Optional examples to guide AI greeting generation
Additional context to guide AI greeting generation, for example the name of the agent, the name of the lead, etc. ALWAYS USE the user's first name and last name in the greeting {{lead.first_name}} {{lead.last_name}}
The language of the greeting, set for future use on MultiLingual Agents
multi, bg, ca, cs, da, da-DK, de, de-CH, el, en, en-US, en-AU, en-GB, en-NZ, en-IN, es, et, fi, fr, fr-CA, hi, hu, id, it, ja, lt, lv, no, nl, pl, pt, pt-BR, pt-PT, ro, ru, sk, th, th-TH, tr, uk, vi, zh, zh-CN, zh-TW, zh-HK The IDs of the mentions to be resolved and provided with value/description in the greeting system prompt
Deprecated. Use structured_greetings instead.
"CHAT_HISTORY"
Was this page helpful?