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

Wispr Flow Voice Actions API

The Voice Actions API from Wispr Flow — 2 operation(s) for voice actions.

Wispr Flow Voice Actions API is one of 50 APIs that Wispr Flow publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Voice Actions. The published artifact set on APIs.io includes an OpenAPI specification.

This API exposes 2 operations across 2 paths, and defines 20 schemas. It is described by OpenAPI 3.2.0, at version 0.5.2.

Requests are made against the base URL https://api.wisprflow.ai.

2 operations 2 paths 20 schemas 2 GET

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.5.2
Base URL
https://api.wisprflow.ai
Authentication
API Key, API Key
Resource Areas
1

Authentication & Security 2

Wispr Flow Voice Actions API declares 2 security schemes for authenticating requests. An API key is passed in the header as Authorization (ApiKeyHeaderPatched). An API key is passed in the header as X-API-Key (APIKeyHeader).

Paths & Operations 2

Across 2 paths, the API surfaces 2 operations — 2 GET. Each is listed below with its method, path, parameters, and response codes.

Voice Actions 2
GET
/api/v1/voice-actions/realtime/schema
Voice Actions Realtime Schema
voice_actions_realtime_schema → 200
GET
/api/v1/voice-actions/realtime/client-schema
Voice Actions Realtime Client Schema
voice_actions_realtime_client_schema → 200

Schemas 20

The contract defines 20 schemas that model the data the API accepts and returns. The most detailed are VoiceActionsAudioAppend (6 properties), VoiceActionsSessionStart (5 properties), VoiceActionsToolCall (4 properties), VoiceActionsToolResult (3 properties). Each schema is shown below with its type and property counts.

VoiceActionsSessionUpdate
object
Refresh the desktop context mid-session (app/textbox/AX context lands after session.start).
2 properties 1 required
VoiceActionsPong
object
Server keepalive frame answering a client ping.
2 properties 1 required
VoiceActionsSessionReady
object
Server frame confirming the session is open, naming the provider and model.
3 properties 2 required
VoiceActionsPing
object
Client keepalive frame; the server answers with a pong.
2 properties 1 required
VoiceActionsToolResult
object
Client frame returning the result of a tool call the model requested.
3 properties 3 required
VoiceActionsError
object
Server frame reporting an error during the session.
3 properties 2 required
VoiceActionsSessionClose
object
Client frame that closes the voice-actions session.
1 property 1 required
VoiceActionsAudioCommit
object
Client frame committing the buffered audio and requesting a model response.
1 property 1 required
VoiceActionsTextInput
object
Final transcript from the client's own ASR pipeline; triggers a model response.
2 properties 2 required
VoiceActionsServerFrameEnvelope
object
Envelope wrapping a single discriminated server frame.
1 property 1 required
VoiceActionsTranscriptFinal
object
Server frame carrying the finalized input transcript.
2 properties 2 required
VoiceActionsTextDelta
object
Server frame carrying an incremental chunk of the model's text response.
2 properties 2 required
VoiceActionsDone
object
Server frame signaling the model response turn is complete.
1 property 1 required
VoiceActionsTextFinal
object
Server frame carrying the finalized model text response.
2 properties 2 required
VoiceActionToolDefinition
object
A tool the client exposes to the model for this voice-actions session.
3 properties 1 required
VoiceActionsAudioAppend
object
Client frame appending a chunk of PCM16 audio to the session's input buffer.
6 properties 2 required
VoiceActionsClientFrameEnvelope
object
Envelope wrapping a single discriminated client frame.
1 property 1 required
VoiceActionsTranscriptDelta
object
Server frame carrying an incremental chunk of the input transcript.
2 properties 2 required
VoiceActionsSessionStart
object
Client frame that opens a voice-actions session with instructions, tools, and context.
5 properties 1 required
VoiceActionsToolCall
object
Server frame requesting the client invoke a tool with the given arguments.
4 properties 4 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

wisprflow-ai-voice-actions-api-openapi.yml Raw ↑

Other APIs Wispr Flow publishes across the network.

Wispr Flow Analytics API
Wispr Flow Analytics Registry API
Wispr Flow Attribution Tracking API
Wispr Flow Authentication API
Wispr Flow Automations API
Wispr Flow Calendar API
Wispr Flow Connectors API
Wispr Flow Cost Centers API
Wispr Flow Dash API
Wispr Flow Dictionary API
Wispr Flow Enterpret API
Wispr Flow Enterprise API
Where this information came from

This is an independent, third-party profile of Wispr Flow Voice Actions 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.