New: Chrome extension — dictate on any website

Voice-enable every CRM and CMS text field in minutes

SpeechOS is an embeddable voice SDK that adds Dictate, AI Edit, Voice Commands, and Read Aloud to every text box in your product.

  • Dictate: polished text with punctuation and filler removed
  • AI Edit: shorten, rewrite, translate, or summarize by voice
  • Commands: trigger workflows like "log activity" and "submit form"
  • Read: have any text spoken aloud instantly
BOOK DEMOTry the live demo
DICTATE

“um so I just uh finished the quarterly report and like the main takeaway is that revenue grew 15 percent”

OUTPUT

3× faster than typing<500ms latency

TECHNICAL SPECIFICATIONS

INPUT SPEED

~3×

vs. typing

ERROR RATE

20.4%

fewer errors

DICTATION

160+

words/min

LATENCY

<500

milliseconds

Source: Stanford HCI text entry study

BUILT ON BEST-IN-CLASS INFRASTRUCTURE

Deepgram - Speech-to-Text AI
Groq - Fast LLM Inference
LiveKit - Real-Time Audio/Video Infrastructure

Typing kills CRM data quality and slows publishing

When text entry is hard, users leave fields blank, write shorter notes, and "fix it later." OS dictation usually produces raw transcripts that still need cleanup.

The old way

  • 01

    Type everything manually

    Slow, error-prone, leads to blank fields and sparse notes

  • 02

    Use OS dictation

    Messy output, no editing workflow, no app commands

  • 03

    Build voice in-house

    Months of edge cases, ongoing maintenance, and no analytics

With SpeechOS

  • 01

    Speak naturally into any field

    Users dictate at 160+ WPM, 3× faster than typing

  • 02

    SpeechOS polishes in real time

    Dictate, edit with voice commands, or read text aloud for proofreading

  • 03

    Add voice commands for workflows

    "Log activity", "submit form", "read this back", and measure adoption

HOW IT WORKS

Two ways to integrate

Use the automatic widget for instant voice UX, or call the SDK directly for full control.

Widget (automatic)

Initialize once. The widget appears automatically when users focus text inputs or select text. Handles dictation, editing, commands, and read-aloud with zero additional code.

  • Auto-detects input, textarea, contenteditable
  • Read-aloud on text selection
  • Works with React, Vue, vanilla JS
Preview the widget

SDK (programmatic)

Call the API directly for custom UIs or headless integrations. Full control over when and how voice actions are triggered.

  • dictate(), edit(), command(), tts.speak()
  • Build your own UI or go headless
  • React hooks: useDictation, useEdit, useTTS
See code examples

INCLUDED MODULES

Voice modules for CRM & CMS teams

Four ways SpeechOS upgrades text entry across your product.

01220+ WPM

CRM Data Capture

Capture call outcomes immediately with polished dictation. No more "I'll update it later."

  • Structured summaries: objections, next steps, outcomes
  • Clean output by default (punctuation + filler removed)
  • Faster entry: ~161 WPM dictation vs ~40 WPM typing

Source: Stanford HCI mobile text entry study

02800+ WPM

CMS Creation + Editing

Draft pages, descriptions, and releases by voice, then refine with simple commands.

  • Edit with commands: "make it shorter", "translate to French"
  • Keep terminology consistent with custom vocabulary + snippets
  • Publish faster with fewer revisions
03INSTANT

Workflow Automation

Define custom commands like "log activity", "create task", or "mark as won". Map intent to actions instantly.

  • Trigger any in-app action or API
  • Intent matching even with varied phrasing
  • Hands-free control for power users and accessibility
04INSTANT

Read Aloud

Users select text and tap Read to hear it spoken naturally. Perfect for proofreading long-form content, accessibility, or reviewing before submitting.

  • Instant text-to-speech with natural voices
  • Proofread by ear before publishing or sending
  • Accessibility for users who prefer audio

See it in action

Try dictating, editing with voice commands, reading text aloud, and controlling the interface with your voice. No signup required.

Book a demo call

Try it on real websites with the Chrome extension

Dictate into Gmail, Notion, Slack, and anywhere you can type.

Add to ChromeLearn more

USE CASES

Built for CRM & CMS workflows

See how product teams are using SpeechOS to transform text entry in their applications.

For CRMs

Speed up contact logging, deal notes, and activity tracking. Capture details without breaking the workflow.

See CRM examples

For CMS platforms

Create and edit product pages, blog posts, and marketing copy by voice.

See CMS examples

For support + ticketing

Let agents dictate replies and internal notes with consistent tone and terminology.

See support examples

For Developers

Ready to add voice to your app?

Our JavaScript SDK gives you dictation, AI editing, and voice commands in a few lines of code.

View Docs

FOR DEVELOPERS

Ship Voice Input in Minutes

Drop in the SDK once. SpeechOS appears on every CRM/CMS text field automatically. Three simple steps to add voice capabilities to any web application.

View Full Documentation
01

Install the SDK

Add SpeechOS to your project with a single command. Available via npm for any web app or with React bindings.

bash
# For any web app
npm install @speechos/client
 
# Or for React apps
npm install @speechos/react
02

Initialize with Your API Key

Get your API key from the dashboard and initialize SpeechOS. The widget automatically appears when users focus on text fields.

typescript
import { SpeechOS } from '@speechos/client';
 
// Initialize with your API key
SpeechOS.init({
  apiKey: 'YOUR_API_KEY',
});
03

Your Users Start Speaking

The widget appears automatically. Users click the mic to dictate, edit with voice, read text aloud, or trigger custom voice commands. Zero configuration required.

Dictate
Edit
Command
Read

Privacy-first by default

We built SpeechOS for enterprise teams handling sensitive data. Privacy and security aren't afterthoughts. They're core to how we operate.

Business use only

Built for organizations, not consumer apps

Real-time streaming

Audio is streamed and processed in real-time, not stored by default

You control the data

Customer is typically the controller; SpeechOS acts as a processor

DPA available

Data Processing Addendum available for customers

Read the Privacy PolicyRequest security documentation

Make your CRM or CMS faster to use and easier to fill out

Ship voice dictation, AI editing, and in-app commands without building your own speech stack.

BOOK DEMOJoin the waitlist

Prefer to build? View docs