Voiceitt

Voiceitt builds inclusive voice AI — automatic speech recognition designed for people with non-standard speech, including speech disabilities, aging adults, and accented speakers. Its speaker-independent and personalized speech-to-text power an AAC/dictation app, live captioning integrations for Zoom, Microsoft Teams, and WebEx, a Chrome extension, and Alexa smart-home control. Developers integrate the same engine through the Voiceitt HTTP API (JWT-authenticated audio-file transcription at api2.voiceitt.com) and a Socket.IO WebSockets API for real-time streaming recognition with partial results.

Voiceitt publishes 3 APIs on the APIs.io network: WebSockets API, Auth API, and Rec API. Tagged areas include Speech Recognition, Speech-to-Text, Voice, Accessibility, and Assistive Technology.

The Voiceitt catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Voiceitt’s developer surface includes documentation, API reference, getting-started guide, support, pricing, signup flow, authentication, and 18 more developer resources.

🌐 Visit website 📡 Source on GitHub
48.1/100 developing ▬ flat Agent 61/100 agent native Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
3 APIs 1 MCP Servers
Speech RecognitionSpeech-to-TextVoiceAccessibilityAssistive TechnologyArtificial IntelligenceTranscriptionCaptioningCompany

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 48.1/100 · developing
Contract Quality 14.6 / 25
Developer Ergonomics 13.0 / 20
Commercial Clarity 10.5 / 20
Operational Transparency 0.0 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 61/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 6 / 6
Agent Skills 5 / 5
Well-Known Catalog 4 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/voiceitt: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

Voiceitt WebSockets API

Socket.IO WebSockets API for real-time speech recognition. After JWT login via the HTTP API, clients set recognition options (set_options), then send recognize_audio_samples for...

Voiceitt Auth API

The Auth API from Voiceitt — 3 operation(s) for auth.

Voiceitt Rec API

The Rec API from Voiceitt — 1 operation(s) for rec.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

voiceitt-mcp.yml

MCP SERVER

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Voiceitt WebSockets API

Socket.IO WebSockets API for real-time speech recognition of non-standard speech. Clients authenticate with a JWT (token + refresh_token in the Socket.IO auth option, obtained f...

ASYNCAPI

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Voiceitt Authentication

http · 1 scheme

SECURITY

Voiceitt Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 3

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference
 AsyncAPI
AsyncAPI

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt
LLMsTxt
 WellKnown
WellKnown
 MCPServer
MCPServer
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conformance
Conformance
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conventions
Conventions
 DataModel
DataModel

Access & Security 3

Authentication, authorization, and security posture

Authentication
Authentication
 Compliance
Compliance
 DomainSecurity
DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support
Support

Commercial 3

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 2

The organization behind the API

Website
Website
 LinkedIn
LinkedIn

Other 1

Properties that don't map to a standard resource type

Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: voiceitt
name: Voiceitt
description: Voiceitt builds inclusive voice AI — automatic speech recognition designed for people with non-standard speech,
  including speech disabilities, aging adults, and accented speakers. Its speaker-independent and personalized speech-to-text
  power an AAC/dictation app, live captioning integrations for Zoom, Microsoft Teams, and WebEx, a Chrome extension, and Alexa
  smart-home control. Developers integrate the same engine through the Voiceitt HTTP API (JWT-authenticated audio-file transcription
  at api2.voiceitt.com) and a Socket.IO WebSockets API for real-time streaming recognition with partial results.
url: https://raw.githubusercontent.com/api-evangelist/voiceitt/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- techstars
x-tier: profile
x-tier-reason: enriched-provider-with-public-api
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
image: https://cdn.prod.website-files.com/64bcd35b2013e5d1f0557e8c/64bce732fa9c2b4c2df390a5_voiceittLogo.svg
tags:
- Speech Recognition
- Speech-to-Text
- Voice
- Accessibility
- Assistive Technology
- Artificial Intelligence
- Transcription
- Captioning
- Company
apis:
- name: Voiceitt WebSockets API
  description: Socket.IO WebSockets API for real-time speech recognition. After JWT login via the HTTP API, clients set recognition
    options (set_options), then send recognize_audio_samples for pre-segmented speech or stream_audio_samples / stream_compressed_audio
    for continuous PCM (16 kHz mono) or compressed audio, receiving chronologically ordered recognition and partial_recognition
    events with segment timing.
  humanURL: https://voiceitt-si-api.readme.io/reference/getting-started-with-your-api-1
  baseURL: https://web.voiceitt.com/socket.io
  tags:
  - Speech-to-Text
  - Streaming
  - Real-Time
  properties:
  - type: Documentation
    url: https://voiceitt-si-api.readme.io/reference/getting-started-with-your-api-1
  - type: AsyncAPI
    url: asyncapi/voiceitt-websockets-asyncapi.yml
  aid: voiceitt:voiceitt-websockets-api
- aid: voiceitt:voiceitt-auth-api
  name: Voiceitt Auth API
  description: The Auth API from Voiceitt — 3 operation(s) for auth.
  humanURL: https://voiceitt-si-api.readme.io/
  baseURL: https://api2.voiceitt.com
  tags:
  - Auth
  properties:
  - type: OpenAPI
    url: openapi/voiceitt-auth-api-openapi.yml
  - type: Documentation
    url: https://voiceitt-si-api.readme.io/reference/getting-started-with-the-voiceitt-rest-api-copy
- aid: voiceitt:voiceitt-rec-api
  name: Voiceitt Rec API
  description: The Rec API from Voiceitt — 1 operation(s) for rec.
  humanURL: https://voiceitt-si-api.readme.io/
  baseURL: https://api2.voiceitt.com
  tags:
  - Rec
  properties:
  - type: OpenAPI
    url: openapi/voiceitt-rec-api-openapi.yml
  - type: Documentation
    url: https://voiceitt-si-api.readme.io/reference/getting-started-with-the-voiceitt-rest-api-copy
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://voiceitt.com/
- type: DeveloperPortal
  url: https://developer.voiceitt.com/
- type: Documentation
  url: https://voiceitt-si-api.readme.io/
- type: APIReference
  url: https://voiceitt-si-api.readme.io/reference
- type: GettingStarted
  url: https://voiceitt-si-api.readme.io/reference/getting-started-with-the-voiceitt-rest-api-copy
- type: Support
  url: https://www.voiceitt.com/faq
- type: Pricing
  url: https://www.voiceitt.com/faq
- type: SignUp
  url: https://web.voiceitt.com/
- type: TermsOfService
  url: https://www.voiceitt.com/legal/terms-of-service
- type: PrivacyPolicy
  url: https://www.voiceitt.com/legal/privacy
- type: LinkedIn
  url: https://www.linkedin.com/company/voiceitt
- type: LLMsTxt
  url: llms/voiceitt-llms.txt
- type: Authentication
  url: authentication/voiceitt-authentication.yml
- type: WellKnown
  url: well-known/voiceitt-well-known.yml
- type: MCPServer
  url: mcp/voiceitt-mcp.yml
- type: Overlay
  url: overlays/voiceitt-rest-api-overlay.yaml
- type: Conformance
  url: conformance/voiceitt-conformance.yml
- type: Compliance
  url: https://www.voiceitt.com/
- type: ErrorCatalog
  url: errors/voiceitt-problem-types.yml
- type: Lifecycle
  url: lifecycle/voiceitt-lifecycle.yml
- type: Conventions
  url: conventions/voiceitt-conventions.yml
- type: DataModel
  url: data-model/voiceitt-data-model.yml
- type: AsyncAPI
  url: asyncapi/voiceitt-websockets-asyncapi.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DomainSecurity
  url: security/voiceitt-domain-security.yml
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 14
  pass: local-v1