top of page


Puzzle SDK
Access Puzzle AI's
core technologies
directly in healthcare
platform environments
Puzzle SDK is a modular set of speech and LLM APIs designed for easy integration across EHR, PACS, and mobile applications
It provides a consistent experience across mobile, web, and desktop environments, and scales efficiently without adding operational complexity.
Access to the core speech recognition technologies behind Puzzle AI products
It packages the same speech recognition input capabilities into an SDK designed for easy integration across any HIS platform enabling partners to adopt proven voice functionalities.



Voice Recognition
Convert Words
Template Creation
Medical Terms
AI: E2E LLM Training
Keep your existing systems.
Move workflows to voice
Implement voice driven input and control alongside existing systems to increase
efficiency, reduce administrative burden while allowing clinicians to focus more time on patient care.
White Label Integration Solution
Maintain existing system environments and functionality
while enabling voice-based input and control
across workflows
Scalability
Supports multiple platforms and programming languages,
allowing seamless integration into existing systems
by any development team
Flexibility
Extends voice-based workflows without additional UX/UI redesign, maintaining the existing user experience
Efficiency
An all-in-one integrated solution that enables
continuous access to additional features
through a single integration
Configurable with all HIS Environments

EHR | EMR
Systems
Voice-enabled documentation across all clinical records within existing systems

PACS & Medical
Imaging
Enables clinicians to create image interpretations, documentation, and annotations

Nursing
Documentation
Mobile-first support enables seamless EHR-linked documentation anytime, anywhere

Remote & Hands-Free Patient Care
Hands-free documentation during telemedicine sessions and surgical or procedural workflows
Designed so engineers at any level
can build quickly
Puzzle SDK is intentionally simple and easy to understand, allowing engineers at any level to add voice input with minimal code while keeping existing input methods unchanged.
Field selection
Select fields where voice input is required
(e.g., key, tag name)
Add Code
Insert provided
function codes
Voice Recognition Enabled
Voice input are enabled for applied text boxes

The moment you speak, documentation and system control happen instantly
Through natural speech and voice commands, clinicians can handle everything from medical records to system control. Experience workflows completed by voice instead of clicking and typing.
Radio buttons,
Checkbox, Select Inputs
“Name: John Smith”,
“Gender: Male/Female”
Set Prescriptions
by Voice
“Patient: Jane Carter”, “Set prescription: Acetaminophen
or Sedative”
Instant
Chart Retrieval
“Michael Johnson”, “Patient”, “Show previous records”
Free-Text
Input
“Subjective clinical
information…”
Select the Deployment That Fits Your Environment
Available in both cloud-based and on-premise deployment options.
Choose the optimal approach based on your organization’s scale and security requirements.
Cloud-based
Fast deployment and easy
scalability
Ideal for individual
users and clinics

On-premise
Optimized for security and
regulatory compliance
Designed for enterpise
organizations and institutions
bottom of page