How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Phonic

Phonic agents API

The agents API from Phonic — 5 operation(s) for agents.

Documentation Provider Profile APIs.io OpenAPI GitHub

Phonic agents API is one of 10 APIs that Phonic publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

Tagged areas include Agents. The published artifact set on APIs.io includes an OpenAPI specification, an AsyncAPI specification, API documentation, an API reference, and a getting-started guide.

This API exposes 9 operations across 5 paths, and defines 65 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against a single base URL, https://api.phonic.ai/v1.

9 operations 5 paths 65 schemas 2 DELETE2 GET2 PATCH2 POST1 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://api.phonic.ai/v1
Authentication
HTTP Bearer
Resource Areas
1

Authentication & Security 1

Phonic agents API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (bearerAuth).

  • bearerAuth — Bearer authentication header of the form Bearer . Manage your API keys [here](https://phonic.co/api-keys).

Paths & Operations 9

Across 5 paths, the API surfaces 9 operations — 2 DELETE, 2 GET, 2 PATCH, 2 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

agents 9
GET
/agents
List
list 2 params → 200404500
POST
/agents
Create
create 2 params body → 201400401404500
PUT
/agents/upsert
Upsert
upsert 2 params body → 200400404
GET
/agents/{nameOrId}
Get
get 3 params → 200403404
DELETE
/agents/{nameOrId}
Delete
delete 3 params → 200403404
PATCH
/agents/{nameOrId}
Update
update 3 params body → 200400403404
POST
/agents/{nameOrId}/custom-phone-numbers
Add Custom Phone Number
add-custom-phone-number 6 params body → 200400401403404409
DELETE
/agents/{nameOrId}/custom-phone-numbers
Delete Custom Phone Number
delete-custom-phone-number 3 params body → 200400401403404409
PATCH
/agents/{nameOrId}/phone-numbers
Update Phone Number
update-phone-number 3 params body → 200400401403404409

Schemas 65

The contract defines 65 schemas that model the data the API accepts and returns. The most detailed are UpdateAgentRequest (49 properties), UpsertAgentRequest (48 properties), Agent (47 properties), CreateAgentRequest (46 properties). Each schema is shown below with its type and property counts.

AgentsNameOrIdPhoneNumbersPatchRequestBodyContentApplicationJsonSchemaConfigurationEndpoint
object
When not null, the agent will call this endpoint to get configuration options for calls on this phone number.
3 properties 1 required
DataRetentionPolicyOneOf1Transcripts
object
1 property 1 required
AgentsNameOrIdCustomPhoneNumbersPostRequestBodyContentApplicationJsonSchemaConfigurationEndpoint
object
When not null, the agent will call this endpoint to get configuration options for calls on this phone number.
3 properties 1 required
AgentPronunciationDictionaryItems
object
2 properties 2 required
AgentToolsItems
CreateAgentRequest
object
46 properties 1 required
ValidationErrorError
object
1 property 1 required
AgentObservabilityIntegrationsItems
string
UpdateAgentRequestConfigurationEndpoint
object
When not null, at the beginning of the conversation the agent will make a POST request to this endpoint to get configuration options.
3 properties 1 required
UpsertAgentRequest
object
48 properties 1 required
CreateAgentRequestObservabilityIntegrationsItems
string
agents_upsert_Response_200
object
3 properties 3 required
CreateAgentRequestToolsItems
agents_update_phone_number_Response_200
object
1 property 1 required
Agent
object
47 properties 32 required
agents_add_custom_phone_number_Response_200
object
1 property 1 required
AgentProject
object
The project the agent belongs to.
2 properties 2 required
BasicErrorError
object
2 properties 1 required
UpdateAgentRequestToolsItems0
string
Built-in tool
CreateAgentRequestConfigurationEndpoint
object
When not null, at the beginning of the conversation the agent will make a POST request to this endpoint to get configuration options.
3 properties 1 required
UpdateAgentRequestToolsItems
CreateAgentRequestMultilingualMode
string
If "auto", each user audio is automatically identified for the language to respond in. If "request", user must request to change language (recommended). If "in…
BuiltInToolConfigSpeechBeforeToolCall
string
Controls whether the assistant speaks before the tool is called. required: the assistant must speak first. optional: the model decides. suppressed: the assista…
agents_get_Response_200
object
1 property 1 required
UpdateAgentRequestIntelligenceLevel
string
The intelligence level of the agent. high uses a more capable model for more complex reasoning, while standard is optimized for lower latency.
CreateAgentRequestPhoneNumber
string
When set to null, the agent will not be associated with a phone number. When set to "assign-automatically", the agent will be assigned a random phone number. W…
DataRetentionPolicy0
object
Zero data retention mode. No transcripts or audio recordings are retained.
1 property 1 required
CreateAgentRequestTemplateVariables
object
2 properties 1 required
DataRetentionPolicyOneOf1AudioRecordings
object
1 property 1 required
CreateAgentRequestPronunciationDictionaryItems
object
2 properties 2 required
Error
CreateAgentRequestIntelligenceLevel
string
The intelligence level of the agent. high uses a more capable model for more complex reasoning, while standard is optimized for lower latency.
AgentAudioFormat
string
The audio format of the agent. If the agent has a phone number, the audio format will be mulaw8000.
agents_update_Response_200
object
3 properties 3 required
AgentMultilingualMode
string
If "auto", each user audio is automatically identified for the language to respond in. If "request", user must request to change language (recommended). If "in…
AgentConfigurationEndpoint
object
When not null, the agent will call this endpoint to get configuration options.
3 properties 3 required
BuiltInToolConfigs
object
Per-tool configuration overrides for built-in tools, keyed by built-in tool ID (e.g. toolnaturalconversationending). A built-in tool referenced in tools but ab…
AgentTemplateVariables
object
1 property 1 required
UpdateAgentRequestBackgroundNoise
string
The background noise type. Can be "office", "call-center", "coffee-shop", or null.
CreateAgentRequestToolsItems0
string
Built-in tool
UpdateAgentRequestObservabilityIntegrationsItems
string
CreateAgentRequestBackgroundNoise
string
The background noise type. Can be "office", "call-center", "coffee-shop", or null.
UpdateAgentRequestPhoneNumber
string
When set to null, the agent will not be associated with a phone number anymore. When set to "assign-automatically", the agent will be assigned a random phone n…
UpdateAgentRequestPronunciationDictionaryItems
object
2 properties 2 required
CreateAgentRequestAudioFormat
string
The audio format of the agent.
agents_delete_custom_phone_number_Response_200
object
1 property 1 required
ValidationError
object
2 properties 2 required
DataRetentionPolicy1
object
Standard data retention with configurable deletion windows.
3 properties 3 required
UpdateAgentRequestTemplateVariables
object
2 properties 1 required
LanguageCode
string
ISO 639-1 language codes supported by the agent
agents_delete_Response_200
object
1 property 1 required
UpdateAgentRequestMultilingualMode
string
If "auto", each user audio is automatically identified for the language to respond in. If "request", user must request to change language (recommended). If "in…
BasicError
object
1 property
AgentIntegration
object
A third-party integration enabled for an agent.
4 properties 4 required
UpdateAgentRequest
object
49 properties
DataRetentionPolicy
Controls how long transcripts and audio recordings are retained before deletion. When zerodataretention is true, nothing is retained and transcripts/audiorecor…
AgentToolsItems0
string
Built-in tool
Task
object
2 properties 2 required
UpdateAgentRequestAudioFormat
string
The audio format of the agent.
OutboundNumberPool
object
Pool of phone numbers used for outbound calls.
2 properties 2 required
AgentIntelligenceLevel
string
The intelligence level of the agent. high uses a more capable model for more complex reasoning, while standard is optimized for lower latency.
agents_list_Response_200
object
1 property 1 required
agents_create_Response_201
object
2 properties 2 required
BuiltInToolConfig
object
Configuration for a simple built-in tool (keypadinput, naturalconversationending, or choosenottorespond).
1 property 1 required
AgentBackgroundNoise
string
The background noise type. Can be "office", "call-center", "coffee-shop", or null.

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

phonic-agents-api-openapi.yml Raw ↑

Other APIs Phonic publishes across the network.

Phonic apiKeys API
AE Profile APIs.io
Phonic auth API
AE Profile APIs.io
Phonic conversationItems API
AE Profile APIs.io
Phonic conversations API
AE Profile APIs.io
Phonic extractionSchemas API
AE Profile APIs.io
Phonic projects API
AE Profile APIs.io
Phonic tools API
AE Profile APIs.io
Phonic voices API
AE Profile APIs.io
Phonic workspace API
AE Profile APIs.io
#Agents
← Back to P APIs
API Details
ID
phonic:phonic-agents-api
Base URL
https://api.phonic.ai/v1
Docs
https://docs.phonic.co/
Provider
Phonic
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=phonic-agents-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/phonic-agents-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of Phonic agents API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.