SITEBORNE SIGNAL MODULE

VoiceBridge Lite — live captions and voice input

Adds explicit-consent voice input or captions with a complete text alternative.

Try the demonstration Add to a project brief

BUSINESS OUTCOME

What this capability changes.

Accessible input
Live captions
Faster content capture

Best for

Accessibility-focused organizations, Events, Content teams

AI: requiredStatus: active

From $2,500

Care from $200/month

Illustrative allowance usageAvailable

PLAIN LANGUAGE, TECHNICAL PROOF

What VoiceBridge Lite does.

Lets someone speak instead of type, or turns spoken material into readable captions, with a complete text alternative.

Why it is valuable

It makes input faster and more accessible while preserving consent and a conventional keyboard path.

A real-world use

An event attendee dictates a question, confirms the transcript, and submits text rather than an opaque audio file.

FOR TECHNICAL READERS

How the control model works

Microphone access begins only after an explicit action. Browser speech recognition is an optional convenience; production transcription uses a bounded provider adapter and never records in the background.

Failure path: Text input, uploaded transcript, or manual caption workflow.

INTERACTIVE WALKTHROUGH

Use VoiceBridge Lite before discussing it.

Type a short spoken passage or use supported browser voice input, then convert it into readable caption segments.

The interaction uses your input and identifies whether it runs locally, checks this live site, or previews a production control. It does not disguise seeded output as intelligence.

Spoken passage or transcript

Microphone access is requested only after you press the button. Typed input always works.

JavaScript-free explanation

This demonstration enhances inputs in the browser. The module page documents its evidence restrictions, fallback, allowance, and upgrade path without requiring JavaScript.

System view

Required

speechmatics, cloudflare-workers

Optional

None

Fallback

Text input, uploaded transcript, or manual caption workflow.

Provider dependencies

speechmatics, cloudflare-workers

Last verified

2026-08-02

Provider limits, terms, model availability, and pricing may change. Production accounts remain client-owned.

Data classification

Audio stream
Transcript

LAUNCH ALLOWANCE

Realtime transcription

Low-volume captions and voice input.

Current limit: 20 realtime hours/month and two concurrent sessions.
Expected light use: Occasional live captions or voice input, with limited batch transcription for supplied recordings.
What consumes it: Realtime minutes, batch minutes, and concurrent realtime sessions.
Fallback: Text input, uploaded transcript, or manual caption workflow.
Paid successor: Speechmatics paid plan or approved transcription adapter
Commercial use: Commercial use permitted subject to current terms.
Data warning: Explicit microphone consent; no background recording; verify regional requirements.
Last verified: 2026-08-02

Upgrade triggers

transcription hours — 75%. Warn client and review paid capacity.
concurrency — 2 sessions. Queue or deny additional sessions safely.

Conventional fallback: Text input, uploaded transcript, or manual caption workflow.

View implementation proof

Decision rationale

The implementation favors semantic HTML, static rendering, typed content, and isolated on-demand routes. Optional AI never controls pricing, eligibility, or emergency routing.

Controls

WCAG 2.2 AA target
Provider-neutral adapters
Usage caps and kill switches
Client-owned production accounts
Conventional fallbacks

Verified evidence

The browser demonstration runs from a clean clone without a paid credential.
Kill switch and allowance states are typed configuration.
Primary navigation and contact paths remain independent of this module.

Known limitation

External provider allowances and production behavior require owner accounts and deployment-time verification.