Clinical documentation · Production

JotPsych launches behavioral health ambient AI scribe using AssemblyAI speech-to-text APIs

The problem

JotPsych needed to build a behavioral health ambient AI scribe capable of handling multi-speaker clinical sessions with high accuracy and speed, but faced a critical build-vs.-buy decision about whether to invest scarce engineering resources in speech-to-text infrastructure or in their core differentiator of behavioral health-specific workflows.

Workflow diagram · grounded in source
1
Multi-participant session begins
trigger
“Mental health sessions often involve multiple participants: therapists, patients, family members, or group therapy settings”
2
Real-time audio transcription
ai_action
“Implementing real-time transcription via Universal-Streaming has enabled us to provide more real-time offerings”
3
Speaker diarization
ai_action
“Speaker diarization enables JotPsych to accurately attribute statements in therapy sessions involving multiple participants”
4
PII redaction
validation
“Speech Understanding models like Speaker Diarization and PII redaction”
5
Clinical documentation output
output
“high-quality transcription forms the foundation for reliable clinical documentation that meets healthcare compliance standards. Fast transcription turnaround times mean clinicians can complete documentation immediately after sessions whi…”
Reported outcome

By integrating AssemblyAI's APIs from day one, JotPsych achieved rapid commercial growth in its first year, saved engineering time on infrastructure, and reduced documentation time for clinicians, allowing the team to focus on behavioral health-specific workflow innovations.

Reported metrics
Engineering time on infrastructureengineering time savings on infrastructure
Customer growth in first commercial yeargrow very quickly in our first commercial year
Documentation time for cliniciansreduction in documentation time for clinicians
Reported stack
AssemblyAIUniversal Speech-to-TextUniversal-Streaming Speech-to-TextSpeaker Diarization
Source
https://www.assemblyai.com/customers/jotpsych
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

By integrating AssemblyAI's APIs from day one, JotPsych achieved rapid commercial growth in its first year, saved engineering time on infrastructure, and reduced documentation time for clinicians, allowing the team to…

What tools did this team use?

AssemblyAI, Universal Speech-to-Text, Universal-Streaming Speech-to-Text, Speaker Diarization.

What results were reported?

Engineering time on infrastructure: engineering time savings on infrastructure; Customer growth in first commercial year: grow very quickly in our first commercial year; Documentation time for clinicians: reduction in documentation time for clinicians (source-reported, not independently verified).

How is this clinical documentation AI workflow structured?

Multi-participant session begins → Real-time audio transcription → Speaker diarization → PII redaction → Clinical documentation output.

Related clinical documentation cases