Remote Support
Currency
AUD
Toggle Nav
Call Us: 1300 551 778
My Cart

SpeechLive AI Speech Recognition

 

SpeechLive AI Speech Recognition

Smarter than traditional speech recognition. Built for the way professionals actually work.

Dictate live at the cursor on Windows or Mac, use real-time recognition on mobile or in SpeechLive, or record first and process the audio in the background. Choose a standard transcript, Smart Transcript, Smart Refine, multi-speaker output, summaries or advanced insights.

Available with SpeechLive Pro and SpeechLive Enterprise. Hosted in Australia on Microsoft Azure, with VoiceX onboarding, training and support included.

Real-time speech recognition at the cursor
Live speech recognition on mobile and web
Recorded-audio recognition from multiple sources
Smart transcripts, summaries and professional review
SpeechLive AI Speech Recognition desktop app for real-time speech-to-text at the cursor

Five ways to use SpeechLive AI speech recognition

Choose the method that suits the task — all with the same licence.

Your dictations, meetings, interviews and conversations automatically transcribed from speech-to-text with SpeechLive AI Speech Recognition

On your Windows or Mac computer

SpeechLive AI Speech Recognition on Windows and Mac
Dictate at the cursor Real-time speech recognition directly into supported applications, documents, emails and browser fields. Explore at-cursor recognition → Record first. Process later. Submit pre-recorded audio from a mobile app, dictation recorder or third-party file for background recognition. Explore background recognition → Capture audio and text live Record dictation, meetings, interviews or conversations in SpeechLive while the text appears in real-time and the audio is retained for later review. Explore browser recording →

On the SpeechLive Mobile App

SpeechLive Mobile App speech recognition
Record and submit for recognition Capture dictations, meetings, interviews or conversations and send them for background processing. Explore recorded mobile dictation → See the text appear as you speak Use real-time speech recognition directly in the SpeechLive Mobile App and add it to any application or send for review in the SpeechLive workflow.Explore real-time mobile recognition →

1. Real-time speech recognition on Windows and Mac

Dictate directly at the cursor.

The SpeechLive Desktop App provides an always-available speech recognition control. Place the cursor in a supported text field and speak. The recognised text is inserted where the document is being created.

  • Dictate into supported documents, emails, browser fields and business applications.
  • Add names, terminology, abbreviations and uncommon expressions to your personal vocabulary.
  • Create reusable voice commands for signatures, clauses, addresses and frequently used text.
  • Use a built-in microphone or professional hardware such as a Philips SpeechMike or SpeechOne.
  • Use the same licensed account from Windows or Mac in different work locations.
SpeechLive Desktop App providing real-time speech recognition at the cursor

2. Background and deferred speech recognition

Record the audio first, then let SpeechLive process it.

Background recognition is ideal when the author does not want to remain at the computer while the document is created. Record naturally, submit the audio and continue with other work.

  • Use audio created in the SpeechLive Mobile App.
  • Upload dictation from professional recorders such as Philips DPM or compatible OM SYSTEM devices.
  • Upload supported audio supplied by a client, colleague or other third party.
  • Review the recognised text yourself or route it to an administrator, assistant or typist.
  • Keep the original audio available for checking and foot-control playback.
Recorded audio submitted to SpeechLive for background speech recognition

3. Live recognition in the SpeechLive Browser Recorder

Capture the audio and recognised text together.

Record a dictation, meeting, interview or conversation in SpeechLive while the text appears live. Because the original audio is retained, the result can be checked immediately or routed for correction.

  • Review and edit the recognised text immediately after recording.
  • Send the audio and text to an administrator, assistant or typist.
  • Use a SpeechMike for traditional dictation.
  • Use a SpeechMike Ambient for dictation, consultations, meetings or conversations.
  • Combine a headset microphone with a foot control for hands-free dictation.
SpeechLive Browser Recorder capturing live text and original audio

4. Recorded speech recognition from the Mobile App

Record on mobile and submit for background recognition.

Capture dictations, meetings, interviews, consultations or conversations in the SpeechLive Mobile App and submit the recording for recognition within the SpeechLive workflow.

  • Add details and attachments before sending the recording.
  • Select the appropriate recognition or AI output.
  • Review the text yourself or route it to an administrator or typist.
  • Keep the original audio available for checking where required.
SpeechLive Mobile App recording submitted for background speech recognition

5. Real-time speech recognition on mobile

Speak into your phone and see the text immediately.

The SpeechLive Mobile App can convert speech to text while the user dictates, making it practical to create content away from the computer without waiting for background processing.

  • View recognised text while speaking.
  • Use the text immediately on the mobile device.
  • Keep the content in SpeechLive or send it for proofreading, depending on the configured workflow.
  • Use the same SpeechLive account as the desktop and browser applications.
Real-time speech recognition in the SpeechLive Mobile App

Choose the output that suits the recording

SpeechLive goes beyond one type of speech-to-text.

Traditional dictation, a client meeting and a multi-person interview require different outputs. SpeechLive lets the user choose how the recording should be processed.

Standard SpeechLive speech recognition output

Standard speech recognition

Creates text that stays close to the words spoken. This suits traditional dictation where the author speaks punctuation and structure, or where a typist will complete the final document against the original audio.

SpeechLive Smart Transcript option

Smart Transcript

Applies punctuation and basic text formatting to create a cleaner, easier-to-read transcript while keeping the spoken content recognisable.

SpeechLive Smart Refine option

Smart Refine

Improves grammar, punctuation and readability while preserving the original meaning. Users can select a professional business or legal style.

SpeechLive Multi-Speaker Transcript option

Multi-Speaker Transcript

Separates speakers and adds time-coded speaker sections, making meetings, interviews, consultations and group discussions easier to follow.

SpeechLive Quick Recap and Detailed Summary options

Quick Recap and Detailed Summary

Quick Recap provides a short overview for rapid understanding. Detailed Summary extracts the essential points and presents the main content in a structured form.

SpeechLive Advanced Insights option

Advanced Insights

Identifies important topics, tasks and possible follow-up actions from longer recordings, providing a useful starting point for professional review.

Human-in-the-loop review

Keep the speed of AI with the control professional documents require.

SpeechLive can retain the original recording alongside the recognised text. That gives the author, administrator, assistant or typist a reliable source for checking names, details and wording before the document is approved or used.

  • Review recognised text directly in SpeechLive.
  • Route work from authors to nominated typists or teams.
  • Use priorities, attachments and dictation properties.
  • Use compatible transcription foot controls for efficient playback and correction.
  • Continue using traditional transcription when full human document creation is required.

Learn more on the SpeechLive dictation and transcription workflow page.

Human review of recognised text against the original audio

Moving from Dragon Professional Anywhere or Dragon Legal Anywhere?

Keep familiar real-time dictation and add more ways to work.

VoiceX recommends SpeechLive AI Speech Recognition as a practical replacement for organisations that want cloud speech recognition at the cursor without limiting users to one method of document creation.

Familiar capabilities

  • Real-time speech recognition at the cursor.
  • Personal vocabulary for names and specialist terminology.
  • Reusable voice commands for standard text.
  • Professional microphone support.
  • Central user administration for multi-user sites.

Additional SpeechLive capabilities

  • Windows and Mac access for the licensed user.
  • Real-time and recorded speech recognition on mobile.
  • Browser recording with live text and retained audio.
  • Background processing from recorders and uploaded audio.
  • Smart Transcript, Smart Refine, multi-speaker output, summaries and insights.
  • Professional author-to-typist workflow and human review.

SpeechLive plans

Choose SpeechLive Pro or SpeechLive Enterprise as the foundation.

AI Speech Recognition can be added to an existing Pro or Enterprise subscription or purchased together as a complete package. The right plan depends on user numbers, administration, security and integration requirements.

SpeechLive Pro logo

SpeechLive Pro + AI Speech Recognition

Suitable for individual professionals and smaller teams that want real-time recognition, recorded-audio processing, mobile dictation and professional workflow in one service.

SpeechLive Enterprise logo

SpeechLive Enterprise + AI Speech Recognition

Designed for larger firms and organisations that require broader administration, deployment controls, security, reporting and supported enterprise integrations.

Licence management for changing teams

  • Named-user access is managed centrally by the account administrator.
  • A licence can be reassigned when a staff member or role changes.
  • Additional licences supplied by VoiceX can be co-termed to the existing subscription and invoiced pro rata.
  • Sites can manage authors, typists, office managers, teams and workflow relationships from one account.

For multi-user firms and organisations

Central administration without managing separate speech products.

Administrators can manage users and workflow relationships from the SpeechLive account, while Enterprise deployments can support broader identity, reporting and integration requirements.

Users and workflow

Add or remove users, assign packages, create teams and define author-to-typist relationships.

Identity and deployment

Support Microsoft Entra ID Single Sign-On and user provisioning where required, with central rollout options for larger Windows environments.

Reports and developer options

Access workflow reports and supported developer options such as API tokens and webhooks for suitable implementations.

Supported business integrations

SpeechLive supports integrations including Actionstep, iManage, NetDocuments and Clio. Availability and features can vary by plan and connected-platform configuration.

Actionstep iManage NetDocuments Clio

Go beyond speech recognition

Add structured document generation when transcription is not enough.

SpeechLive AI Assistants include the SpeechLive AI Speech Recognition capabilities described on this page, then add document generation, templates and industry-aware AI assistance.

SpeechLive Legal AI Assistant on desktop and mobile

SpeechLive Legal AI Assistant

From legal dictation and supporting files to a structured document.

SpeechLive Legal AI Assistant understands legal context and maps information from dictation and supporting sources into a selected template. Users can combine audio with documents, PDFs and images, then review and refine the generated document before approval.

  • Includes the complete SpeechLive AI Speech Recognition feature set.
  • Supports firm templates and AI-assisted template creation.
  • Allows natural-language editing and refinement.
  • Keeps professional review and SpeechLive workflow options available.

Explore SpeechLive Legal AI Assistant

SpeechLive Professional AI Assistant — coming soon

AI document creation for general professional work.

SpeechLive Professional AI Assistant will extend the same document-generation approach to broader professional use, creating structured outputs from dictation, meetings and other spoken content without a legal-specific vocabulary and template set.

  • Will include SpeechLive AI Speech Recognition capabilities.
  • Will support professional document generation and reusable templates.
  • Will retain human review before documents are approved or distributed.
Placeholder for SpeechLive Professional AI Assistant

Australian hosted. Local implementation and support.

SpeechLive supplied, configured and supported by VoiceX.

SpeechLive is hosted in Australia on Microsoft Azure for Australian customers. VoiceX provides local onboarding, configuration, training and ongoing support as part of the solution.

  • Help selecting SpeechLive Pro or Enterprise and the AI Speech Recognition package.
  • Setup for authors, typists, administrators, teams and workflow relationships.
  • Training for desktop, browser, mobile, recorder and review functions.
  • Advice on microphones, recorders, headsets and transcription foot controls.
  • Local assistance for trials, rollout and ongoing use.
VoiceX onboarding, training and Australian support for SpeechLive

See every method with one user licence

Trial SpeechLive AI Speech Recognition in the places your users actually work.

Test live dictation on Windows or Mac, real-time and recorded mobile speech recognition, browser recording, background processing and professional review with VoiceX support.