Send Calls - Cekura

Authorizations

X-CEKURA-API-KEY

string

header

required

API Key Authentication. It should be included in the header of each request.

Body

call_id

string

required

Unique identifier for the call. Example:

"call_abc123xyz"
"stereo_audio_session_456"

Maximum string length: 100

agent

integer

Agent ID, required if assistant_id not provided Example: 2421

assistant_id

string | null

Provider's Assistant ID, required if agent not provided Example:

"asst_abc123xyz"
"agent_xyz789"

voice_recording

string<uri> | null

Audio recording file of the call. Example: Binary data "recordings/call_123_20240315.mp3"

voice_recording_url

string<uri> | null

URL to call recording audio file Example: "https://storage.example.com/recordings/call_123.mp3"

transcript_type

enum<string>

write-only

Format of the transcript_json payload. Tells Cekura how to parse roles and timestamps.

vapi — Vapi webhook format: [{"role": "bot"|"user", "message": "...", "time": 0.0}]
retell — Retell webhook format
elevenlabs — ElevenLabs format
livekit — LiveKit format
pipecat — Pipecat format
deepgram — Deepgram format
cekura (default) — [{"role": "Testing Agent"|"Main Agent", "content": "...", "start_time": 0.0, "end_time": 2.5}]. Valid roles are "Testing Agent" and "Main Agent" only — using "agent" or "user" will return a validation error.
none-mono — mono audio with no transcript; Cekura generates the transcript automatically.

Omit this field to use the default Cekura format.

cekura - cekura
vocera - vocera
vapi - vapi
retell - retell
deepgram - deepgram
pipecat - pipecat
livekit - livekit
elevenlabs - elevenlabs
none-mono - none-mono

Available options:

cekura,

vocera,

vapi,

retell,

deepgram,

pipecat,

livekit,

elevenlabs,

none-mono

transcript_json

any

Call transcript in supported format (Vapi, Retell, Deepgram, ElevenLabs, Cekura)

Check the Transcript Format documentation for more details.

Cekura Transcript Format Example:

[
   {
      "role": "Testing Agent",
      "content": "Hello.",
      "end_time": 1.9399999,
      "start_time": 1.4399999
   },
   {
      "role": "Main Agent",
      "content": "Hello. I want to book appointment today. My name is John.",
      "end_time": 7.539999511718751,
      "start_time": 3.1
   },
   {
      "role": "Testing Agent",
      "content": "Well, I mean, sure. What time exactly are we talking about here",
      "end_time": 15.71,
      "start_time": 12.01
   },
   {
      "role": "Main Agent",
      "content": "6 PM.",
      "end_time": 18.269999,
      "start_time": 17.609999
   }
]

call_ended_reason

string | null

Reason why the call ended Example:

"customer-ended-call"
"agent-ended-call"

customer_number

string | null

Customer's phone number or identifier Example:

"+1234567890"
"customer_abc123"

metadata

any

Additional call metadata Example:

{
    "customer_id": "123",
    "order_id": "ORD-12345",
    "name": "John Doe"
}

timestamp

string<date-time>

When the call occurred. Example: 2024-03-15T10:15:45Z

dynamic_variables

any

Dynamic variables used to replace {{variables}} in agent description. Example:

{
    "subscription_id": "SUB-12345",
    "product_type": "premium"
}

feedback

string | null

Feedback about the call Example: "Great call"

redact_fields

enum<string>[]

Optional list of sensitive fields to redact from the transcript and audio. If not provided, no redaction will occur. Available fields include: phone_number, email_address, credit_card, ssn, dob, healthcare_number, etc. Note: Redacting any fields incurs a cost of 0.4 credits per minute, regardless of how many fields are selected. Example: ["phone_number", "email_address", "credit_card"]

person_name - person_name
age - age
phone_number - phone_number
email_address - email_address
date - date
time - time
location - location
origin - origin
gender_sexuality - gender_sexuality
physical_attribute - physical_attribute
occupation - occupation
username - username
password - password
ip_address - ip_address
url - url
filename - filename
event - event
vehicle_id - vehicle_id
dob - dob
healthcare_number - healthcare_number
medical_professional - medical_professional
credit_card - credit_card
account_number - account_number
bank_account - bank_account
money - money
ssn - ssn
passport_number - passport_number
driver_license - driver_license
numerical_pii - numerical_pii

Available options:

person_name,

age,

phone_number,

email_address,

date,

time,

location,

origin,

gender_sexuality,

physical_attribute,

occupation,

username,

password,

ip_address,

url,

filename,

event,

vehicle_id,

dob,

healthcare_number,

medical_professional,

credit_card,

account_number,

bank_account,

money,

ssn,

passport_number,

driver_license,

numerical_pii

metric_ids

string

write-only

Comma-separated metric IDs to evaluate for this call. Example: "118,119". To run metrics after the call is created, use the evaluate_metrics endpoint instead.

main_agent_channel_index

integer | null

Channel index (0 or 1) of the main agent in stereo recordings. When provided, skips automatic channel detection. Example: 0 means channel 0 is the main agent, channel 1 is the customer/testing agent.

Response

call_id

string

required

Unique identifier for the call. Example:

"call_abc123xyz"
"stereo_audio_session_456"

Maximum string length: 100

integer

read-only

duration

string

read-only

Call duration in minutes in MM:SS format. Example: 01:10

success

boolean | null

Whether the call was successful. Example: true or false

is_reviewed

boolean

Whether the call has been reviewed. Example: true or false

status

enum<string>

Status of the call or conversation. Example: "completed" or "failed"

success - Success
failure - Failure
reviewed_success - Reviewed Success
reviewed_failure - Reviewed Failure

Available options:

success,

failure,

reviewed_success,

reviewed_failure

feedback

string

Feedback about the call. Example: "Great Call"

metrics

object[]

read-only

Metrics of the call

Show child attributes

call_ended_reason

string

Reason why the call ended. Example:

"customer-ended-call"
"agent-ended-call"

Maximum string length: 100

customer_number

string

Customer's phone number or identifier. Example:

"+1234567890"
"customer_abc123"

Maximum string length: 100

agent

integer | null

Agent ID

agent_name

string

read-only

Agent name

timestamp

string<date-time>

When the call occurred. Example: 2024-03-15T10:15:45Z

error_message

string | null

dropoff_point

string

Point in conversation where user disengaged. Example: "end of conversation as no queries remaining"

Maximum string length: 1000

topic

string

Topic of the call. Example:

"product_inquiry"
"technical_support"

Maximum string length: 1000

created_at

string<date-time>

read-only

When this record was created. Example: 2024-03-15T10:30:45Z

updated_at

string<date-time>

read-only

When this record was last updated. Example: 2024-03-15T10:35:11Z

transcript

string

Full text transcript of the call. Example:

[00:01] Testing Agent: Hello. 
[00:02] Main Agent: Hello, how can I help you today?
[00:03] Testing Agent: Well, I mean, sure. What time exactly are we talking about here
[00:04] Main Agent: 6 PM.
[00:05] Testing Agent: Great. I'll book that for you. Just a sec.
[00:06] Main Agent: Okay.

transcript_object

any | null

Structured transcript data with timestamps. Example:

[
    {
        "role": "Testing Agent",
        "content": "Hello",
        "start_time": 1.2,
        "end_time": 1.8
    },
    {
        "role": "Main Agent",
        "content": "Hello, how can I help you today?",
        "start_time": 1.8,
        "end_time": 2.5
    }
]`

evaluation

string

read-only

Evaluation of the call

API Reference

Documentation Index

Authorizations

Body

Response