How it works...

Step 1 - Create or receive audio

Create or Receive audio recording with up to 10 speakers. The better the audio quality and equipment used, the better results you will have.

Step 2 - Upload to SpeechLive

Upload recording to SpeechLive ecosystem.
File is now available to assistants and other staff for review as well.

Step 3 - Send to Speech Engine

Text document is returned in less time than total mins of the recorded audio. Ex: 10 Min audio complete in less than 10 min.

Multiple Speaker Speech To Text

Philips SpeechLive uses AI technology to perform speaker diarization on the recorded audio in order to detect who is speaking and when.

• Up to 10 speakers
• Speakers are identified as 1, 2, 3...
• Auto punctuation
• Multiple file types supported
• Great for depositions, interviews, meetings, & interrogations

View Pricing

Video Demonstration

Pricing and Recording Bundles

SpeechLive w/ Multi-Speaker Speech-to-Text

Each user will have access to all the features of the SpeechLive Ecosystem. Including the transcription workflow features. This feature is currently in beta phase and when it is completed it may require an additional fee to use in the future.

• Per speech recognition user per year
• Includes Desktop speech recognition App
• Includes Smartphone recording app with SR
• Online speech recognition on web
• Convert  recorded audio to text
• Fair use flat rate (see more)

*Larger accounts may require Enterprise plan

Conference Recording Bundle

Create higher quality recordings to improve the output of the speech to text document.

SmartMike Duo for Conversations

Great for interviews and conversations with only 2 speakers. Transcript happens in real-time.

Specification requirements

More About SpeechLive...

Other Speech Recognition Methods Included

Smartphone - Backend

Smartphone - Frontend

Browser - Frontend

Desktop - Frontend

All speech recognition workflows are available during a trial and available upon purchase as an add-on package to your SpeechLive user subscription. Please see pricing at the end of this page.

View Speech Recognition Options PDF

Dictation Recorder

Use the SpeechLive Smartphone app on your Android or iPhone to create dictation or voice memos to be later transcribed. The recorder is a full featured recording solution that allows for rewind and playback, insert and overwrite, and custom dictation properties and text comments.

• Full featured dictation recorder
• Route Dictation to a team or individual typist. 
• Optional Philips 3rd party transcription service available
• Send as audio with or without speech recognized text
• Real-time job statuses
• Apple Watch Companion Recorder App Available!

SpeechLive App

Speech Recognition

As a speech recognition tool, you can use the Philips SpeechLive app to create documents on the fly. Easily dictate into the app and view the transcribed text instantly. Copy the text to be used in an email or create a document from your mobile device. 

• Instant Transcription
• Up to 7 times faster than typing
• Real-time upload to your typist for editing
• Supports up to 22 languages
• Up to 95% accuracy

View Speech Recognition Video

Transcription Workflow

Transcribe from anywhere.

With Philips SpeechLive you can transcribe from anywhere. Access dictation and your transcription software from any computer directly in a web browser.
Working from home has never been easier when the work comes to you!

• Web Based Transcription Software
• Desktop Based Software - Syncs with the cloud
• "Pickup where you left off" mode from any computer
• Email and desktop notifications of new dictation

Dictation Workflow

Dictation Routing

Dictation files can be routed many different ways with SpeechLive. Full info: Click Here

• Default - Dictation routes to default typist/s
• Workpool - All dictation goes to all typists
• Direct Assignment - Author chooses specific typist
• Teams Assignment - Author sends to custom typist team
• Transcription Admin - Dictation can be reassigned