Solutions
Ambient Listening
in Healthcare
Ambient listening — the technology behind modern AI medical scribes — captures clinical encounters in real time and generates structured documentation without dictation or typing. Here's how Scribeberry implements ambient listening with privacy-first architecture and clinician-controlled review.
Real-time speech capture
Audio streams to the cloud in 1-2 second chunks. No persistent recording. Speaker labels (provider vs patient) auto-detected.
Privacy-first architecture
Audio is never permanently stored. Regional data residency (Canada or US). Patient data is never used to train AI models. BAAs with all sub-processors.
Clinician always in the loop
AI drafts; clinician reviews and signs. No note is ever finalized without human review. Uncertain phrases are flagged for verification.
About Ambient Listening in Healthcare
Ambient listening is the audio capture model where a microphone listens passively to the full encounter — versus dictation, where the clinician speaks discrete commands to the mic. Ambient is the modern standard for AI medical scribes because it preserves natural patient-provider conversation while still generating structured notes.
Scribeberry's ambient listening pipeline starts at consent. The CPSO, CMPA, and most US state medical boards require explicit patient consent before clinical audio recording. Scribeberry surfaces the consent prompt at scribe creation and auto-documents the consent in the chart.
Audio is captured by the device microphone, streamed in real-time to a HIPAA-compliant cloud (Microsoft Azure, Google Cloud, or OpenAI under BAA depending on the deployment region), transcribed by a clinical speech-to-text model, and structured by a clinical LLM into the chosen note template.
FAQ
What is ambient listening in healthcare?
Ambient listening is the technology that powers modern AI medical scribes. A microphone captures the natural patient-provider conversation during a clinical encounter, and AI converts the audio into a structured clinical note that the clinician reviews and signs.
Is ambient listening secure?
Reputable ambient listening platforms (including Scribeberry) stream audio without persisting it, encrypt all data in transit (TLS 1.3) and at rest (AES-256), and maintain regional data residency. Always verify HIPAA, PIPEDA, and SOC 2 Type 2 compliance with your vendor.
Does ambient listening capture other conversations in the room?
Speaker labeling separates provider and patient voices. Background conversations (hallway noise, intercom announcements) are typically not transcribed if they're below a noise threshold. For shared exam rooms, position the mic close to the patient-provider conversation.
What happens to the audio after the encounter?
Scribeberry never stores audio permanently. The audio stream ends when the recording stops. Only the transcript and final note are retained — and they're encrypted, audit-logged, and deletable on demand.
Compare more
