SpeechMax™

Features Table

More than a word processor™ A custom speech and text processor . . . .
Editions Full, Multimedia, Reader
  Reader available as FREE download
Full All features, incl. My AV Notebook™, The Talking Form™
  Advanced speech and language processing
Multimedia Includes My AV Notebook
  Speech-oriented multimedia, organize multimedia
Reader (aka Reader/Viewer/Player) Session files locked by license (not opened w/passkey)
  Read files from Full or Multimedia editions
User configurable document protection Optional lock in Full, Multimedia editions
  Lock/unlock with passkey
Windows Main, document, annotation
  Open one or more document windows
Toolbars and menu items Vary by edition
  Reader most restrictive
Multiwindow Open one or more document windows
  Annotation window for each document window
Multilingual Unicode-enabled
  Document/annotation windows language independent
Main window File, Edit, Actions, Tools, Plugins, Windows, Help Menus
  Toolbar items
File Open, save, print
  Save except in Reader
Edit Copy, cut, paste
  Except in Reader
Actions, Tools Display, process audio, text, or image content
  Limited in Multimedia and Reader editions
Plugins for SR, TTS Requires speech recognition, text to speech engine
  NA Multimedia, Reader editions
Window, Help Available with all editions
  Most recent Help available online
Document window Menu items/toolbars for read/write text, audio, images
  Open one or more document windows
Files Read/write session, other files
  Open different files in different windows
Annotation window One or more audio or text annotations (annotation tab)
  Includes tab for audio splitting (w/speech analysis)
Multilevel annotations One or more text and/or audio annotations per text link
  Text link number determined by user
Informational/activation annotations Informational audio and text comments
  Text annotations may launch programs, link to web
Features (document window)  
Forms creation Create "fill-in-the-blank" templates (The Talking Form™)
  Use with structured dictation into fields
Playback speech, music, or other audio Audio playback (session file audio)
  May use w/USB Infinity transcriptionist footpedal
Other playback options Play audio file with external playback software
  e.g., PlayBax™, other similar application
Playback/record Install and configure USB devices
  Requires HID compliant
Utterance (segment) playback With menu, button, shortcut key, or device
  Next, previous, continuous auto playback
Selected text playback Highlight text, playback associated audio
  With button, shortcut key, or device
 Text editor Create/edit text, add audio, graphics or images
  Output .html, .rtf, .txt
Session file editor Create/edit session text, add audio, graphics or images
  .ses (CSUSA), .html, .xml, .rtf, .txt
Speech engines supported Dragon, IBM, Microsoft, SAPI 5.x
  May transcribe audio with SpeechServers™
Session file support .csf, .ses (CSUSA), .dra (Dragon)
  Open, edit, and save .dra session file

Extract audio/play Dragon

 Extract .wav from .dra session file
  Playback .dra session file w/foot control
Session file w/manual transcription .ses (CSUSA)
  Untranscribed, transcribed session files
Untranscribed session file Use SpeechSplitter™ w/SweetSpeech™
  Create segmented audio for transcription
Separate/merge segments Multiple transcriptionists, centrally merged final text
  ScrambledSpeech™ available also
Multiwindow editing w/text comparison Open two or more read/write windows
  Compare texts in same or different languages
Multiwindow display Same as Microsoft Windows
  Horizontal, vertical, cascade, max/min
Multilingual/Unicode enabled May vary language by window
  English, Spanish,  Arabic, Chinese, etc.
Recent files Lists recently opened documents
  May select to open
Copy/cut/paste Copy/cut to clipboard, paste from clipboard
  Paste as text or HTML
Restore Undo, redo
  Disaster recovery (start point configurable)
Spellchecker Customizable, supports Stedman's
  Use for English, other languages
Macro editor User configurable, various options
  Text expander, auto find/replace, other
Formatting Bulleted and numbered lists, font selection
  Bold, italics, underline, style sheet, other
Text alignment Align text to margins
  Left, right, center, justify
Text flow Primarily for translation
  Aligns corresponding L to R and R to L text
Find/replace Same as Microsoft Windows
  Search for/replace text in document
Select highlight color Highlight text
  Use standard or custom colors
Show HTML With reference to current document
  Displays .html code in Microsoft Notepad
Shortcut keys Keyboard shortcuts
  Execute commands
Print Preview/Print View document before printing
  Choice of printers
Insert Header/Footer/Untagged Insert nondictated text
  For identification, not used for training
SpeechTracker™ No sound dropout with routine text edit
  Audit trail maintained
SpeechCensor™ Clear audio + text ==> deidentify confidential information
  HIPAA, security, other applications
ScrambledSpeech™ Divide/reorder data for completion or editing
  Limit content and order available to any party
Clear text Removes text from document or session file
  If session file, saves audio w/phrase segments
Synchronized segments Compare multiple drafts or translations
  Use Tab to move to synchronized segment
Advanced text comparison (multiple files) File comparison by phrase or document
  Differences highlighted for rapid error detection
Best result session file Creates composite best-guess from > 2 files
  Highlight differences between other files
DataInSync™ Synchronize session (file) tags
  Create identical segment numbers
TurboTranscribe™ with WordCheck™ Compare synchronized transcribed outputs
  Facilitates rapid correction
VerbatiMAX™ Compare transcribed output with old text
  Rapid correction using old transcription
Differences statistics Total words, errors (total and percentage)
  Inserts, deletions, replacements
SpeechLocate™ Transcribe audio file by > 2 speech engines
  Locate audio using text reference
Generate speech recognition training file Save audio-aligned verbatim text
  Create or train SR speech user profile
Real-time and audio file speech recognition Plugin available
  Dragon, Microsoft, IBM, SAPI 5.x
Text-to-speech Plugin for Dragon, Microsoft, IBM, and other TTS
  e.g., ATT Natural Voices, NeoSpeech
Find large utterances Locate long phrases
  Use split audio and text to shorten for training
Ignore phrase Mark phrase due to poor audio, noise
  Phrase ignored for speech user training
Session file information Includes info re session file
  Audio, engine, and user information
Annotation features  
Annotation Text, text plus audio
  Supports unlimited annotation
Annotation entry Keyboard, sound recorder
  Speech recognition, text to speech
Text comment box Enter text, including URLs, command line
  Unicode compatible
Sound recorder Record microphone speech or music
  REC, FF, REW, insert, overwrite, stop/pause
Transpose/move annotation Swap annotation text for main text OR
  Replace main text with annotation
Multilevel audio or text comments Supports > 1 annotation ID per selected text
  Annotations may be different author, language
MultilinksPRO™ Associate > 1 website per word in text
  Run > 1 program per word in text
Redictation support with annotation Speaker B corrects speaker A
  Use corrections to train speech models A, B
My AV Notebook™ Multimedia presentations
  Create AV Text with voice, music, images
Examples Electronic scrapbook, audio books, lectures
  Singalongs, sales presentations
The Talking Form™ Customizable voice prompts for data entry
  Record prompts or create with text-to-speech
Speech analysis Access with audio splitting tab
  Analyze and resegment speech and audio
Split/merge session file segments Redefine session file phrase boundaries
  Use for creation of training session file
Data migration wizard Export/Import to/from database, XML, .ses session files
  Prepopulate forms (templates), export/import data
Other  
Software Development Kit (SDK) Developer integration tools, including API documentation
  Optional use with Command!™ workflow
Boxed Dragon or runtime compatibility Professional, Medical, or Legal
  v. 8.10.000.285 or higher (only 9.x supported)
Other speech engines Boxed or runtime IBM v. 10 USB Pro
  Microsoft and other SAPI 5.x
Operating system Windows 2000, XP Pro, 2003, Vista
  Requires most recent service pack

Features List

  • Sound Recorder
  • Free-form dictation with built-in sound recorder
  • Structured dictation into categories or "fill-in-the-blank" also available
  • Audio Playback
  • Integrated audio playback with or without transcriptionist foot pedal
  • Requires USB HID compliant device
  • Playback of audio by phrase or sentence
  • Continuous playback of complete audio file with or without highlighted phrases
  • Presegmented audio permits playback of audio or text utterance
  • Use Infinity foot pedal for playback of Dragon and other speech recognition
  • Read/Write Text
  • Creation of text file alone 
  • Keyboard into one or more windows
  • Read/Write Audio-aligned Text (Session File)
  • Creation of session file with audio-aligned text from manual transcription
  • Text selection and playback of associated audio from session file
  • Edit text transcribed manually or with speech recognition
  • Proprietary .csf and .ses session files
  • May include graphics, images, speech, music, or songs
  • See My AV Notebook™ for creation of multimedia with text linked to audio
  • May be created from "empty session file" with segment markings only
  • Standard Formatting
  • Standard Windows formatting for .txt, .rtf, or .html text
  • Bold, italics, underline
  • Indentation, centering
  • Other
  • Other Formatting/Editing
  • Style sheets
  • Undo, redo, restore (disaster recovery)
  • Built-in text expander
  • Advanced macro functions
  • Spell check (including medical and other special vocabularies)
  • Keyboard corrections or paste from another window 
  • Switch/swap text to different read/write window
  • Multiple languages (Unicode)
  • English, Spanish, French, German, Russian, Chinese, Japanese, and other languages
  • Audio-aligned and synchronized translation into one or more languages
  • Plugins for Speech Recognition and Text to Speech
  • Speech recognition
  • SAPI 5.x compatible systems, e.g., Microsoft, SweetSpeech™
  • Other, e.g., Dragon¹, IBM (text output only)¹
  • Dragon, IBM dictation runtime licenses available²
  • FREE license for transcriptionist³
  • Text to speech
  • SAPI 5.x compatible systems, e.g., Microsoft, ATT Natural Voice, NeoSpeech VoiceText
  • ATT, NeoSpeech voice font licenses available²
  • Annotation
  • Text
  • Audio
  • Multiple audio and/or text annotations for each phrase or sentence
  • Same or different language than original text or speaker
  • Annotate by text or audio segment or individual graphic
  • Swap text comments into main read/write window
  • Use speech recognition to enter annotation text as comment or correction
  • Speaker B may correct Speaker A's speech recognition
  • Generate training session file for each speaker
  • Text annotation may open website or open file or execute command line
  • Launch program, open website, or open file with "Run" feature of text annotation
  • File Comparison
  • By segment
  • By document
  • Differences highlighted for easy editing
  • Synchronize segments for transcription by human and/or machine
  • Compare two or more text outputs for error spotting with WordCheck™
  • Edit text by comparing matches for error spotting
  • Save time, "TurboTranscribe™" final text--less audio to listen to and less typing
  • Use patented VerbatiMAX™ techniques to generate verbatim training text for training
  • Reduce manual transcription time by up to 60% with speech recognition
  • Synchronized "Best Guess" or "Best Result" Session File
  • Available for two or more session or text files (8 file limit)
  • Use "Compare Documents" and "Create Best Guess"
  • Combine results based upon occurrence to create most accurate result
  • Use as index session file and compare with other human and/or machine transcription
  • Session processor server available for offline creation of "best guess" file
  • No limit on number of files used to create "best guess" file with offline server
  • Speech Recognition Training Files
  • Use text comparison for rapid creation verbatim text
  • Macros for reverse formatting to speech engine format
  • Forward format to create formatted final text for letters, documents, reports
  • SELECTIVE DELETE
  • Selectively delete text and associated audio in session file
  • SEPARATELY TRANSCRIBE PHRASES
  • Segment audio file
  • Send phrases to different transcriptionists (human or machine)
  • Alternatively, may scramble phrases for transcription by single transcriptionist
  • Merge phrases into final document at central site
  • AudioVisual and Multimedia Session File with Voice, Music, or Songs
  • Use My AV Notebook™ to create audiovisual text and other multimedia
  • Supports audio-linked text

_____________________________________________________

¹ Server-based and real-time speech recognition available for Dragon Professional, Medical, and Legal 9,
Dragon Preferred 9, IBM ViaVoice Professional 10, and SAPI 5.x speech recognition and text to speech,
including AT&T Natural Voices and NeoSpeech VoiceText voice fonts.  System may run with Dragon
Professional, Medical, or Legal v. 8.10.000.285 or higher, but only version 9.x is supported.  System may
run with IBM Professional v.8.x or higher, but only  IBM USB Pro 10.x is supported.   See other products
for pricing and more information.

²  Dragon and IBM speech recognition dictation-only runtimes may be purchased from Custom Speech USA
only for use with the company's products.  Electronic Help manual is included with the runtime, but not
voice commands, printed manual, or headset microphone.  AT&T Natural Voices and NeoSpeech VoiceText
voice fonts runtimes are available for use only with the company's products.   See other products for pricing and
more information. 

³  Software must be provided by speaker and used solely to edit his/her documents.

Price, terms, specifications, and availability are subject to change without notice. Custom Speech USA, Inc.
trademarks are indicated. Other marks are the property of their respective owners.  Dragon and
NaturallySpeaking® are licensed trademarks of Nuance® (Nuance Communications, Inc.)