ABOUT VOCALTEK
Founded in 2008, VocalTek Solutions Inc. is a Montreal based company specializing in state-of-the-art speech processing solutions for professionals in both official languages. Our solutions include dictation, transcription and (front-end or back-end) speech recognition which can be customized and seamlessly incorporated into any desired workflow.
All our solutions are turn-key and guaranteed to enhance productivity. We pride ourselves in providing unparalleled comprehensive training and ongoing technical support from our software engineers for all our solutions to facilitate and ensure a harmonious transition for our clients, enabling them to immediately benefit from a rapid return on their investment.
While our solutions are most often deployed in hospitals, medical clinics, law firms, legal departments, and government agencies, they are nonetheless adaptable and scalable to meet general applications in both large and smaller organizations as well as individuals.
Our SDK solution allows providers to integrate dictation, transcription and/or speech recognition functionalities into their solutions.
To compliment and diversify our product offerings, we’ve partnered with industry leaders such as Philips, the undisputed leader in dictation and transcription equipment as well as workflow software for law firms as well as Nuance, the leader in speech recognition software, to offer best of breed technology to meet our client’s needs and budgets.
HEALTHCARE SOLUTIONS
With an installed base of over a thousand physicians currently benefiting from our speech recognition solutions, VocalTek is uniquely positioned to draw on this experience to fully customize our solutions. Our clients include hospitals, super-clinics, GMF’s, specialty clinics and institutes as well as RIS/PACS providers across Canada. Our speech recognition solution is compatible with all certified EMRs in Quebec (OmniMed, KinLogix, Medesync, Myle, MobileMed, OFYS, and Toubib).
VocalTek is an accredited partner of Nuance for the integration of Dragon Medical One (DMO), a cloud-based front-end speech recognition solution available in both French and English. Additionally, we provide enhancements such as specialized lexicons, templates, dictation macros and custom development.
If you are looking for a complete workflow dictation, transcription and speech recognition solution, our VSpeech solution can be closely integrated with your third-party systems (e.g., a RIS/PACS solution).
VocalTek DMO – Real-time Speech Recognition with Dragon Medical One
- Real-time cloud-based speech recognition for note-taking in an EHR, EMR, or other third-party applications
- Turnkey solution that includes all the necessary components to ensure successful deployment
- Enables data entry at speeds of up to 140 words per minute
- Possibility to add custom templates and dictation macros to further enhance productivity
- Includes a Quebec French general-medicine lexicon developed by VocalTek specifically for the Quebec market
- Quick return on investment
Make an informed choice for clinical documentation
Two approaches. One goal: reducing the burden of clinical notes.
Documentation support technologies are evolving rapidly. Today, clinics often hesitate between two main approaches:
- Medical speech recognition, with Dragon Medical One
- AI scribes, capable of automatically generating a note from a consultation (Care/CoeurWay, Plume IA, etc.)
👉 The right choice depends on your clinical reality, your regulatory requirements, and the level of control you want.
✅ Dragon Medical One
The benchmark for controlled clinical dictation
Dragon Medical One is a real-time medical speech recognition solution designed to allow clinicians to write their own notes quickly and accurately, directly in the EMR.
Why clinics choose DMO?
- Full control over content
Every word is dictated, seen, and validated in real time by the clinician. - Immediate and measurable productivity
No generation delays, no asynchronous steps. - Proven clinical accuracy
Advanced medical vocabulary, accent adaptation, customizable predefined text. - Robust EMR integrations
Recommended for institutional and multi-site environments. - No systematic audio recording storage
Reduces consent, storage, and data governance concerns.
Ideal for:
✔️ Physicians who want to stay in control
✔️ Organizations looking for a mature, tested, and proven technology
🤖 AI Scribes
Maximum automation of the clinical note
AI scribes analyze the consultation (audio or conversation) and automatically generate a structured note: history, exam, plan—sometimes including forms or coded elements.
What they offer
- Structured notes ready for review
- Reduced word-for-word dictation
- Advanced features: CNESST/SAAQ form completion, treatment plan assistance
Worth serious consideration if:
✔️ Consultations are long or repetitive
✔️ The clinician is comfortable thoroughly reviewing a generated note
⚠️ Points to consider
- Recording of consultations (patient consent, data security)
- Variable quality depending on specialty and context
- Requirement for rigorous clinical review to identify hallucinations and omissions
⚖️ How to choose? The right questions to ask
- Control or automation?
Dictate and manage every word, or delegate the initial structure? - Compliance and confidentiality
Where is the data hosted? Who has access? - EMR integration
Real workflow efficiency vs. marketing promises. - Return on investment
Actual time saved, clinician adoption, long-term costs.
✅ The approach recommended by VocalTek
🎯 One single solution? Not always.
In many Quebec clinics, the hybrid approach performs best:
Dragon Medical One for dictation, voice commands, and day-to-day control
AI scribe for certain visit types or as an intelligent draft
👉 Result: efficiency + compliance + clinical acceptance
VSpeech – Dictation, Transcription and Speech recognition Workflow Solution for all-size Medical Establishments
- Advanced workflow options to meet the specific needs of various healthcare facilities and/or departments
- Option to record dictations in real-time speech recognition mode, back-end speech recognition, or standard digital dictation
- Offers physicians the ability to finalize their speech recognition reports themselves or send them, along with the original voice recording, to a transcription secretary for review and correction
- Improves the efficiency of secretaries, as they receive pre-transcribed text, ready for review and correction
- Creation of custom templates and dictation macros to further increase productivity
- Interfacing/integration with third-party applications such as a RIS or PACS
- Centralized administration
- Database driven client-server architecture
- Flexible installation configurations to meet IT infrastructure requirements
SOME EXAMPLES OF SPEECH RECOGNITION DICTATION WITH VSPEECH:
Radiology Specialty – Realtime Speech Recognition: Example 1
Radiology Specialty – Realtime Speech Recognition: Example 2
LEGAL & GENERAL SOLUTIONS
Although VocalTek’s installed base includes some of the largest law firms and government agencies with enterprise solutions, we nevertheless provide a variety of dictation, transcription, and speech recognition hardware and software solutions regardless of size. Our team will work closely with you to optimize the entire document processing workflow.
Our partnership with Philips as a “Master Digital Center Enterprise” ensures that our team is fully trained and qualified to sell, install, configure, customize, train, and support Philips’ entire line of professional hardware and software solutions. Additionally, we are a value-added reseller for Nuance’s Dragon speech recognition software solutions.
Dragon Professional Anywhere – Real-time speech recognition dictation solution
- Professional real-time speech recognition: dictate notes, reports, and emails directly into your applications, without relying on a secretary or an intermediate transcription workflow.
- High and consistent performance: voice input at up to 140 words per minute, with professional-grade accuracy, cloud-hosted for use anywhere.
- Customizable productivity: create custom vocabularies, document templates, and dictation macros to automate repetitive phrases and speed up content creation.
- Simplified deployment and management: secure cloud solution (Microsoft Azure), automatic updates, and centralized administration, compatible with enterprise environments.
- Fast return on investment: reduced data entry time, fewer administrative tasks, and measurable productivity gains within the first weeks of use.
- Security and IT compatibility: encrypted data (256-bit), standards compliance (e.g., HIPAA), and support for virtualized environments (Citrix, VMware, RDS).
Philips SpeechLive – Cloud-based dictation, transcription, and speech recognition solution with AI assistant
- Cloud-Based Accessibility: Operate from anywhere with internet access. SpeechLive’s browser-based platform allows users to dictate, transcribe, and manage documents without the need for local installations, facilitating remote and hybrid work environments.
- SpeechLive also connects with other Philips dictation devices, including the PocketMemo and Philips SpeechMike Premium.
- Collaborative workflow: assignment, tracking, and management of dictations between authors, transcribers, and administrators.
- Advanced Speech Recognition: Utilize AI-powered speech recognition supporting up to 21 languages with support for multiple speakers and automatic punctuation, enabling real-time transcription and reducing the need for manual typing.
- Robust Security Measures: Ensure data protection with double encryption during upload and download processes. Data is stored on Microsoft Azure servers, adhering to international standards such as ISO certifications and GDPR compliance.
- Seamless and flexible integration: SpeechLive integrates effortlessly with your existing workflows and connects to over 1,000 applications through Zapier, including Dropbox, Google Drive, and Salesforce. For specialized use cases, it can also integrate with third-party speech recognition engines such as Dragon Medical or Dragon Legal, ensuring full compatibility with your current tools.
- User-Friendly Interface: Experience an intuitive interface requiring minimal training, enabling quick adoption across teams. The accompanying smartphone app allows users to dictate and manage files on the go, further enhancing mobility and flexibility.
Philips SpeechExec Pro – Professional Dictation, Transcription Workflow Solution
- Tailored for small organizations or individuals
- Dictation with Philips Digital Pocket Memos or Philips SpeechMikes
- Encryption and backup functions
- Popup alerts for notification of new important tasks
Philips SpeechExec Enterprise – Enterprise Dictation, Transcription Workflow Solution
- Tailored for medium to large scale organizations
- Centralized administration
- Remote management of users, workflow settings and hardware devices
- Dictation with smart phones, Philips Digital Pocket Memos or Philips SpeechMikes
- Support of virtualization
SDK SOLUTIONS
VocalTek’s proprietary software development kit (SDK) is used by solutions providers across Canada to cost-effectively integrate dictation, transcription and speech recognition functionalities into their solutions.
INTEGRATION OF THE FOLLOWING WORKFLOWS:
- Digital dictation with transcription by a secretary
- Real-time speech recognition, with report finalized by author
- Real-time speech recognition, with corrections by a transcriptionist
- Back-end speech recognition, with corrections by a transcriptionist
- Playback of completed reports in digital dictation or speech recognition mode
- Synchronization of audio to text during playback
- Integration of speech recognition directly into your preferred text editor
- Server hosted on site or by VocalTek
- Test application and source code available with the SDK, demonstrating the implementation of every integration feature
- Thorough training and technical assistance by VocalTek
CONTACT US
- PHONE: 514-315-2525
- FAX: 514-315-1773
- EMAIL: info@vocaltek.com
FAQ
- Choosing the most appropriate solution to achieve desired workflow
- Optimizing the speech recognition rate from the outset with:
- Specialized and customized lexicons
- User-specific language model(s)
- User-specific acoustic model
- Customizing the solution to maximize efficiency
- Integration with third-party solutions
- Comprehensive user training
- Ongoing support
Speech recognition can be used to significantly reduce the time it takes to create notes as data entry can reach speeds of 140 words per minute
Whether the author completes his notes using real-time speech recognition or forwards the recognized text to a transcriptionist for edition, overall productivity is dramatically increased
Many repetitive tasks can be automated with voice-enabled dictation macros and custom commands
Reduction of administrative burden and associated costs
Reallocation of time savings to more important tasks
Rapid return on investment
- Multiple speech recognition options including Dragon and VSpeech to better serve our clients with the most appropriate solution
- Customization and integration of our solutions within desired workflow
- VocalTek is a Canadian Master Digital Center Enterprise for Philips enabling us to resell, install, train and provide technical support all their professional speech processing products (hardware or software)
- VocalTek is a Canadian value-added reseller for Nuance enabling us to resell, install, train and provide technical support on all Dragon solutions including Medical (DMPE or DMO), Legal and Professional
- The R.O.I. on speech recognition is quite fast as the aim is to reduce the time spent on documentation by at least 25% from the outset
- For instance, if a professional spends 2 hours a day on documentation, he/she can expect to gain an average of 30 minutes per day, 2.5 hours per week or 130 hrs per year. Assuming an average cost of $1,300 per year, the cost of the solution would average $10 for each hour saved.
Copyright © 2026 VocalTek