> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reddy.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Create Call
> Creates a call inside Reddy platform
Check out our [Send Calls to Reddy guide](/guides/send-calls-to-reddy) for examples of using this endpoint.
This endpoint is used to add a call to Reddy and perform the QA grading process on it. QA grading can be triggered by either uploading an audio file or providing a transcript.
Calls are added to a processing queue and may not show up in the dashboard immediately. Processing times vary based on current queue load.
Once the process is completed, the insights will be visible on the dashboard.
The `filename` parameter is optional. If provided, the response will include a signed Google Cloud Storage URL for uploading the audio file. If omitted, a simple success response is returned. Audio files must be under **250 MB**.
Redaction is not applied to the audio if the transcript is provided. If you have sensitive information in the audio that you want to silence, make sure you do that using word-level timestamps in your transcription before sending to Reddy.
## Speaker Separation
Control how speakers are separated in the call using the `speaker` object:
* **speaker.separation**: 'diarize' (default) or 'channels'
* **speaker.channel\_map** (optional, when separation="channels"): \["agent", "customer"] or \["customer", "agent"]. If omitted, roles are identified automatically.
[Learn more about speaker separation](/guides/send-calls-to-reddy#speaker-separation)
```bash cURL with transcript theme={null}
curl -X POST 'https://app.reddy.io/api/v1/call/create' \
-H 'Authorization: Bearer YOUR_API_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"agent_email": "agent@company.com",
"product_id": 123,
"transcript": [
{
"role": "agent",
"text": "Hello, how can I help you today?",
"start": 5,
"stop": 36
},
{
"role": "customer",
"text": "I need help with my recent order",
"start": 54,
"stop": 67
}
]
}'
```
```bash cURL with audio (default diarization) theme={null}
curl -X POST 'https://app.reddy.io/api/v1/call/create' \
-H 'Authorization: Bearer YOUR_API_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"filename": "call_recording.wav",
"agent_email": "agent@company.com",
"product_id": 123
}'
```
```bash cURL with stereo audio (labeled channels) theme={null}
curl -X POST 'https://app.reddy.io/api/v1/call/create' \
-H 'Authorization: Bearer YOUR_API_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"filename": "stereo_call.wav",
"agent_email": "agent@company.com",
"product_id": 123,
"speaker": {
"separation": "channels",
"channel_map": ["agent", "customer"]
}
}'
```
```bash cURL with stereo audio (AI detection) theme={null}
curl -X POST 'https://app.reddy.io/api/v1/call/create' \
-H 'Authorization: Bearer YOUR_API_TOKEN' \
-H 'Content-Type: application/json' \
-d '{
"filename": "stereo_call_unknown.wav",
"agent_email": "agent@company.com",
"product_id": 123,
"speaker": {
"separation": "channels"
}
}'
```
```json Response (with audio) theme={null}
{
"upload_id": 12345,
"conversation_id": "conv_123",
"upload_url": "https://storage.googleapis.com/...",
"expires_in": 3600
}
```
```json Response (with transcript) theme={null}
{
"success": true
}
```
## OpenAPI
````yaml api-reference/openapi.json POST /api/v1/call/create
openapi: 3.1.0
info:
title: Reddy API
version: 1.0.0
description: ''
servers: []
security: []
paths:
/api/v1/call/create:
post:
tags:
- Call
summary: Call Create
description: >-
Triggers the call addition process. If a transcript is provided, the QA
process will be done on that transcript.
Otherwise, it will wait for the audio file to be uploaded.
When a filename is provided, the response includes a signed Google Cloud
Storage URL. Upload the raw audio bytes directly to that URL with the
correct Content-Type header.
The upload URL expires after 1 hour.
operationId: api_standard_api_call_events_call_create
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CallCreateData'
required: true
responses:
'200':
description: OK
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/UploadURLResponse'
- $ref: '#/components/schemas/CallCreateSuccess'
title: Response
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationError'
'404':
description: Not Found
content:
application/json:
schema:
$ref: '#/components/schemas/UserNotFound'
'422':
description: Unprocessable Entity
content:
application/json:
schema:
$ref: '#/components/schemas/ProductNotFound'
'500':
description: Internal Server Error
content:
application/json:
schema:
$ref: '#/components/schemas/CreationError'
security:
- AuthBearer: []
components:
schemas:
CallCreateData:
properties:
filename:
anyOf:
- type: string
- type: 'null'
description: >-
Name of the audio file to be uploaded. Optional - if not provided,
no upload URL will be returned.
title: Filename
agent_email:
description: Email address of the agent handling the call
title: Agent Email
type: string
product_id:
description: Product id associated with the call
title: Product Id
type: integer
channels:
anyOf:
- items:
type: string
type: array
- type: 'null'
description: >-
**DEPRECATED**: Use speaker.separation and speaker.channel_map
instead. Mapping of the channels in the audio file to the customer
and agent. If nothing is specified, speakers will be identified
automatically with a speaker diarization model.
For example: ['customer', 'agent'] means the left channel contains
the customer's audio and right channel contains the agent's audio.
title: Channels
speaker:
anyOf:
- $ref: '#/components/schemas/Speaker'
- type: 'null'
description: >-
Configuration for speaker separation and channel mapping. If not
provided, defaults to diarization.
transcript:
anyOf:
- items:
$ref: '#/components/schemas/TranscriptLine'
type: array
- type: 'null'
description: Transcript of the call
title: Transcript
tags:
anyOf:
- items:
$ref: '#/components/schemas/Tag'
type: array
- type: 'null'
default: []
description: Array of tag objects containing key, value, and type
title: Tags
timestamp:
anyOf:
- type: number
- type: 'null'
description: >-
Timestamp of the call start time in seconds since epoch format. If
not set, defaults to the current time.
title: Timestamp
conversation_id:
anyOf:
- type: string
- type: 'null'
description: Unique identifier for the conversation
title: Conversation Id
required:
- agent_email
- product_id
title: CallCreateData
type: object
UploadURLResponse:
properties:
upload_id:
description: Unique identifier for the upload
title: Upload Id
type: integer
conversation_id:
description: Unique identifier for the conversation
title: Conversation Id
type: string
upload_url:
description: >-
Signed Google Cloud Storage URL to upload the audio file. Send raw
bytes with the correct Content-Type header.
title: Upload Url
type: string
expires_in:
description: Time in seconds for which the upload URL is valid
title: Expires In
type: integer
required:
- upload_id
- conversation_id
- upload_url
- expires_in
title: UploadURLResponse
type: object
CallCreateSuccess:
properties:
success:
title: Success
type: boolean
required:
- success
title: CallCreateSuccess
type: object
ValidationError:
properties:
conversation_id:
description: Unique identifier for the conversation
title: Conversation Id
type: string
error:
description: Validation error message
title: Error
type: string
required:
- conversation_id
- error
title: ValidationError
type: object
UserNotFound:
properties:
conversation_id:
anyOf:
- type: string
- type: 'null'
title: Conversation Id
error:
title: Error
type: string
required:
- error
title: UserNotFound
type: object
ProductNotFound:
properties:
conversation_id:
anyOf:
- type: string
- type: 'null'
title: Conversation Id
error:
title: Error
type: string
required:
- error
title: ProductNotFound
type: object
CreationError:
properties:
conversation_id:
description: Unique identifier for the conversation
title: Conversation Id
type: string
error:
description: Error message
title: Error
type: string
required:
- conversation_id
- error
title: CreationError
type: object
Speaker:
properties:
separation:
anyOf:
- type: string
- type: 'null'
default: diarize
description: >-
Control how to separate the speakers in the call. Options: 'diarize'
(default) - diarize the audio to separate transcripts by speakers
and then identify roles; 'channels' - use pre-separated audio
channels (stereo/multichannel). See channel_map parameter.
title: Separation
channel_map:
anyOf:
- items:
type: string
type: array
- type: 'null'
description: >-
Mapping of audio channels to speaker roles. Only valid when
separation='channels'. If provided, must be exactly 2 elements
containing 'agent' and 'customer' (e.g., ['agent', 'customer'] or
['customer', 'agent']). If omitted when separation='channels', AI
will automatically identify which channel contains which role.
title: Channel Map
title: Speaker
type: object
TranscriptLine:
properties:
text:
description: Text of the transcript
title: Text
type: string
role:
description: Role of the speaker
enum:
- customer
- agent
title: Role
type: string
metadata:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
default: {}
description: Additional metadata associated with the transcript
title: Metadata
timestamp:
anyOf:
- type: number
- type: 'null'
description: Timestamp of the transcript in seconds since epoch format
title: Timestamp
start:
anyOf:
- type: number
- type: 'null'
description: >-
Starting time of the transcript in seconds since the beginning of
the call. If not provided, it will be calculated based on the
timestamp relative to the first utterance.
title: Start
stop:
anyOf:
- type: number
- type: 'null'
description: >-
Ending time of the transcript in seconds since the beginning of the
call. If not provided, it will be calculated based on the timestamp
relative to the first utterance.
title: Stop
required:
- text
- role
title: TranscriptLine
type: object
Tag:
description: |-
Schema representing a tag with a key and value.
The value can be a single value of various types.
properties:
key:
title: Key
type: string
value:
anyOf:
- type: string
- type: integer
- type: boolean
title: Value
type:
enum:
- string
- integer
- boolean
title: Type
type: string
required:
- key
- value
- type
title: Tag
type: object
securitySchemes:
AuthBearer:
type: http
scheme: bearer
````