October has arrived. The decorations are going up, the days are getting shorter, and spooky season is officially underway.

But for courts evaluating speech-to-text technology, ghosts and goblins may not be the scariest thing lurking around the corner.

It might be the promise of “AI-powered,” “proprietary,” or “next-generation” transcription technology that sounds extraordinary in a demonstration—but tells you remarkably little about how it will perform in an actual courtroom.

A new September 2026 resource bulletin from the Joint Technology Committee (JTC), AI-Assisted Transcription in Courts: Governance, Use, and Safeguards, offers courts a timely reality check.

And much of its guidance reinforces something we at Liberty have believed from the beginning:

Speech-to-text should be treated as a powerful tool—not a magic trick (or treat).

Start With the Problem, Not the AI

One of the simplest recommendations in the JTC bulletin may also be the most important:

“Before undertaking an AI-assisted transcription project, courts should identify the specific problem they are trying to solve.”  

That sounds obvious.

Yet the current AI market often encourages organizations to work backward: find an impressive technology first, then determine where it might fit.

Courts deserve better.

Are you trying to make recorded proceedings searchable? Give judges faster access to testimony? Provide draft transcripts? Improve accessibility? Reduce transcription turnaround time? Support staff working through a reporting shortage?

Those are different problems, with different risks and different requirements.

The JTC notes that courts are generally using AI transcription to support digital recording, create draft text, improve searchability, and enhance accessibility—not simply replace certified court reporting.

That distinction matters.

The Recording Still Comes First

Perhaps the bulletin's most significant point is also one of the least glamorous:

Good transcription starts with good audio.

The JTC states plainly that AI-assisted transcription “depends first on a reliable digital recording system for court proceedings.” It goes on to emphasize that clear source audio is foundational to transcript accuracy and that multi-channel recording can help distinguish speakers and support review.

That should change the way courts evaluate STT vendors.

A transcription engine cannot recover information that was never captured clearly in the first place.

Poor microphone pickup, overlapping speakers, courtroom acoustics, HVAC noise, paper movement, side conversations, and inconsistent audio levels can all affect the output. The bulletin specifically warns that real-world courtroom conditions can materially degrade transcription performance.

In other words:

The most impressive AI demo in the world cannot compensate for a bad record.

That is why Liberty has always viewed speech-to-text as part of a broader recording ecosystem—not as a replacement for one.

About That “Proprietary AI”…

Here is where a little healthy skepticism is warranted.

Speech recognition technology has advanced extraordinarily quickly. High-quality engines are increasingly available from major cloud providers, specialized vendors, open-source projects, and other technology platforms.

That is good news for courts.

It also means the phrase “proprietary AI” should begin, not end, the procurement conversation.

• What exactly is proprietary?
• Is the vendor developing the underlying speech-recognition model?
• Are they licensing or integrating another provider's engine?
• Can the transcription engine change over time?
• Where is the audio processed?
• Is court data retained?
• Can it be used for model training?
• What happens if the underlying provider changes?
• And, most importantly:
• How does it actually perform on your recordings?

The JTC recommends precisely that kind of scrutiny.

Courts should test transcription systems using representative local courtroom recordings rather than relying on “vendor claims or generic performance metrics.”

That's a sentence worth remembering.

A carefully prepared demonstration recording is one thing.

A Tuesday morning docket with six speakers, an interpreter, overlapping testimony, rustling papers, somebody sitting too far from the microphone, and an HVAC system that has apparently decided to join the proceeding is another.

Test the latter.

Accuracy Is Not One Number

Another trap is the temptation to reduce transcription performance to a single impressive percentage.

“95% accurate.”

“98% accurate.”

“Industry-leading accuracy.”

Those numbers may sound reassuring, but courts should ask what they actually represent.

The JTC recommends evaluating not just word-level accuracy but material-error rates, correction burden, turnaround time, speaker identification, and failure points in challenging proceedings.

That is much closer to the question courts really need answered.

An incorrect article or conjunction may be annoying.

An incorrect name, dollar amount, date, legal term, speaker attribution, or critical word in testimony can be something very different.

And the bulletin explicitly identifies many of the environments where automated transcription can struggle: overlapping speech, accents and dialects, multilingual proceedings, interpreters, legal terminology, names, dates, numbers, rapid speech, and speaker attribution.

So rather than asking:

“What is your accuracy rate?”

Try asking:

“Show us where your system fails.”

That may be one of the most valuable questions in an STT evaluation.

The Real Value May Be Everything Around the Transcript

In practice, one of the most common ways Liberty customers use speech-to-text today is much simpler: search.

Rather than treating machine-generated text as the official record, courts use it as an index into the recording—searching for a name, phrase, or topic, then jumping back to the corresponding audio to verify what was actually said.

That workflow closely reflects the approach described in the JTC bulletin, which notes that AI-generated text can be used as a shortcut for locating information in the underlying recording and recommends verifying relevant content against the source audio.

And importantly, Liberty does not resell or mark up the speech-to-text service itself.

Today, a court with an Azure account, Liberty Post Recording Manager, and existing recordings can begin batch-processing those files through Azure Speech Services directly. Liberty provides the workflow and integration; the court maintains its own relationship with the transcription provider.

[Learn how to configure speech-to-text in Liberty Post Recording Manager →]

At current Azure pricing (October 2026), that can be approximately $0.18 per processed hour of audio, depending on the service and configuration.

For many courts, that means the value proposition is not “buy our AI.” It is simply: make the recordings you already have dramatically easier to find and use.

This is also why we believe speech-to-text itself will increasingly become a commodity.

The differentiator isn't simply whether software can turn audio into words, the more important questions are what happens next.

• Can a user click into the transcript and hear the corresponding audio?
• Can the system identify speakers based on isolated recording channels?
• Can judges and staff search an entire proceeding?
• Can access be controlled?
• Can confidential proceedings be protected?
• Can retention requirements be honored?
• Can the system integrate into existing court workflows?
• Can the court export its own data?
• Can a better transcription engine be adopted later without replacing the entire recording infrastructure?

Interestingly, the JTC procurement recommendations focus heavily on exactly these surrounding capabilities: synchronized transcript and recording playback, speaker/channel identification, search, audit logs, confidentiality controls, data ownership, retention, security, and protections against vendor lock-in.

That is where we believe courts should concentrate their attention.

AI Transcription Shouldn't Be Scary

None of this means courts should avoid speech-to-text.

Quite the opposite.

AI-assisted transcription has enormous potential to make recorded proceedings easier to search, faster to review, more accessible, and more useful. The JTC describes growing—but appropriately cautious—experimentation across courts and related adjudicative organizations.

At Liberty, we're excited about that future!

We just think courts should be allowed to see the technology for what it is.

Speech-to-text is a tool.

A rapidly improving one.

And increasingly, a widely available one.

That belief also shaped Liberty’s approach to the results themselves. Most courts already have Microsoft Word, so they shouldn’t need a proprietary or cloud-based text editor just to review or search speech-to-text output. As shown in the screenshot above, Liberty can generate standard RTF files that open directly in Word, helping keep the workflow familiar, local, searchable, and simple.

So, this spooky season, don't be frightened by AI. Be wary of the smoke machine.

Ask what is actually powering the system—and what value the vendor is adding around it.

• Test it against your own proceedings.
• Understand where your data goes.
• Measure the errors that matter.
• Require human review where the stakes demand it.

And when someone tells you their transcription technology is unlike anything else on the market?

Maybe ask them to turn the lights on.

Liberty Recording is pleased to announce the official release of Liberty Recording Suite v9.0, the latest version of our integrated court recording, conferencing, and speech-to-text platform.

Version 9.0 builds on Liberty’s long-standing focus: helping courts capture the official record clearly, reliably, and efficiently. This release introduces a wide range of enhancements across Liberty Court Recorder, Liberty Virtual Courtroom, and supporting server components, with a particular emphasis on reducing administrative overhead in hybrid and virtual courtroom environments.

For courts managing remote appearances, virtual hearings, interpreters, private attorney-client discussions, and multi-channel recordings, v9.0 provides a more streamlined way to manage the entire proceeding from one connected platform.

• Download Liberty Court Recorder Updates in v9.0 PDF
• Download 9 Major Liberty Virtual Courtroom Updates in v9.0 PDF

Integrated Recorded Conferencing for the Modern Courtroom

Many courts still rely on separate systems for courtroom recording, video conferencing, remote participant management, and post-hearing review. While this approach can work, it often creates extra administrative burden: staff must manage multiple platforms, coordinate links, track participants manually, and ensure the final record accurately reflects what occurred.

The Liberty Recording Suite takes a different approach.

With Liberty Virtual Courtroom integrated directly into the Liberty recording workflow, remote participants can be managed as part of the proceeding itself. Audio, video, participant activity, and speech-to-text results can all be tied more closely to the official recording environment, helping reduce the number of disconnected steps court staff must manage.

In v9.0, this integrated workflow has been strengthened with improvements to participant controls, private rooms, lobby management, video spotlighting, interpreter controls, connection handling, and recording-file metadata. These updates are designed to help courts conduct virtual and hybrid hearings with less friction and more confidence.

Designed to Reduce Administrative Overhead

The v9.0 release includes several enhancements focused directly on day-to-day court administration.

Conference managers can now move participants between lobbies in real time, helping correct misrouted participants without requiring them to disconnect and rejoin through a different link. This is especially useful for courts managing multiple virtual courtrooms, high-volume dockets, or shared hearing environments.

Version 9.0 also adds configurable Case/Docket/Ticket labels, allowing each court or deployment to use terminology that matches local workflows and jurisdictional standards. Liberty Court Recorder and Liberty Virtual Courtroom automatically retrieve and display this value, reducing the need for workarounds or generic field labels.

For administrators and courtroom staff, small workflow improvements can have a large cumulative effect. Updated conference manager icons, clearer separation between conferencing users and gallery users, improved role color behavior, updated lobby login messages, and expanded customizable labels all contribute to a cleaner and more manageable experience.

Parallel Private Rooms for More Flexible Hearing Management

One of the major Liberty Virtual Courtroom enhancements in v9.0 is the addition of Parallel Private Rooms.

Managers can now conduct private conversations with participants without interrupting the active conference. Calls can take place within a private room environment, and when the private session concludes, participants can be returned to the appropriate location. This helps support workflows such as attorney-client conversations, side discussions, pre-hearing coordination, or private conversations involving court staff.

For courts, this can reduce the need for external communication tools, separate calls, or manual coordination outside the hearing platform.

More Control Over Participant Abilities

Virtual and hybrid hearings require structure. Courts need to determine who can speak, listen, chat, share screens, exchange files, or leave private rooms.

Version 9.0 introduces expanded participant ability controls, allowing conference managers to enable or disable key participant functions during a session. These include self-join, chat, screen sharing, file sharing, and the ability to leave private rooms. Screen sharing and file sharing can also be managed on a per-participant basis.

These controls give courts more flexibility to support different proceeding types while maintaining courtroom order and reducing the need for staff intervention.

Spotlight Video Feeds for Witnesses, Evidence, and Presentations

Liberty Virtual Courtroom v9.0 also adds the ability for a conference manager to spotlight a video feed for all users.

When a participant’s video feed is enlarged for all attendees, that selected feed becomes the primary view, and participants cannot override the manager’s selection. This can be especially helpful during witness testimony, evidence presentation, screen sharing, or any moment where the court needs everyone focused on the same visual source.

This feature helps keep proceedings organized and reduces confusion for remote participants.

Interpreter Controls for Multi-Language Proceedings

Courts increasingly need tools that support accessible, multi-language proceedings. In v9.0, managers can dynamically assign interpreter controls to desktop app users. Assigned interpreters gain specialized controls within their interface, helping structure interpreted proceedings without requiring external coordination tools.

This helps courts support language access needs within the same integrated environment used to manage the hearing and recording.

Improved Recording File Detail and Speech-to-Text Integration

Version 9.0 also improves how information is captured and preserved in the recording workflow.

Broadcast event logs, including mute and unmute events, can now be saved to the DCR recording file. Real-time speech-to-text results can also be included in the recording file as an attachment bookmark.

For courts reviewing proceedings after the fact, these improvements help connect the recording with supporting context, making the record easier to understand, search, and manage.

The release also improves speech-to-text channel naming by using the remote participant’s name in channel labels, creating clearer identification of speakers and remote participants within the recording environment.

Better Stability and Visibility for Remote Participants

Virtual hearing reliability remains critical. Version 9.0 includes improvements to connection stability and reporting, including automatic reconnection attempts for dropped users, improved performance for browser-based participants, and better visibility into connection quality.

These enhancements are especially important for courts working with participants who may be connecting from different devices, networks, and locations.

Built for Court Workflows, Not Generic Meetings

Liberty Recording Suite v9.0 reflects the needs of courts that require more than a standard video meeting platform.

Court proceedings involve dockets, roles, private discussions, interpreters, exhibits, remote participants, official records, and strict procedural expectations. A generic conferencing tool may handle the call, but it does not necessarily support the complete courtroom workflow.

Liberty’s integrated approach helps reduce the administrative load by bringing recording, conferencing, participant management, speech-to-text, and record-related metadata into a unified environment.

Availability

Liberty Recording Suite v9.0 is now officially available.

Courts and existing Liberty customers interested in learning more about the v9.0 release, upgrade planning, or integrated recorded conferencing workflows are encouraged to contact Liberty Recording for additional information.

September 9, 2025

Featuring: Glendale AZ City Court

Introduction

Courts across the country continue to face the challenge of balancing accessibility, efficiency, and reliability in their virtual hearings. General-purpose video conferencing platforms like Zoom, Teams, and Webex, while effective for everyday collaboration, struggle to meet the unique demands of a courtroom setting.

This paper explores the recurring pain points courts face with these platforms, how Liberty Virtual Courtroom is purpose-built to address those needs, and the first-hand experience of Glendale City Court, which transitioned from Zoom to Liberty Virtual Courtroom and saw measurable improvements in time savings, staff efficiency, and participant confidence.

Problem #1: Managing Multiple Virtual Courtrooms

Why Zoom Hearings Take Longer

The National Center for State Courts (NCSC) reports that remote hearings often take up to 34% longer than in-person hearings, with login conflicts and technical difficulties cited as leading causes of delay1. Courts relying on general-purpose platforms like Zoom or Teams struggle when running multiple dockets simultaneously, as login collisions and session timeouts disrupt proceedings and waste staff resources.

How LVC is Built for High-Volume Courts

Liberty Virtual Courtroom (LVC) allows multiple managers to co-manage different virtual courtrooms at the same time without logging out or ending sessions. Staff can seamlessly switch between lobbies and courtrooms, join a colleague's room instantly, and keep every docket moving in parallel. In short: the system was designed for the realities of high-volume courts where several hearings run concurrently every day.

Time Saved in Glendale

Devin McMillion, Court Operations Supervisor in Glendale, confirmed the difference after implementation: "I'd say the biggest thing we've saved is time. We're no longer battling for space on Zoom ... delays could range anywhere from 15 to 45 minutes depending on the number of in-custodies."

He continued: "At times, we had up to four courtrooms running separate Zoom sessions simultaneously. Because of login limitations, one courtroom would often be kicked out ... The process added unnecessary stress, caused delays, and disrupted the overall flow of proceedings. With Liberty, those conflicts are gone."

Problem #2: Process and Clerical Overhead

The Hidden Burden on Clerks

The NCSC has noted that one of the most common complaints about virtual hearings is the increased burden on clerks and staff. When using general-purpose platforms, recordings must often be downloaded, labeled, and manually stored, creating extra steps that introduce risk of error and consume valuable time. In many courts, this clerical overhead translates into hours of repetitive work each week.

How LVC Eliminates Busywork

Liberty Virtual Courtroom captures all in-room and remote audio/video and saves it directly into a single Liberty Court Recorder file - the same secure, evidentiary file used for in-person hearings. Every participant's isolated channel is preserved and merged into the case record automatically. By eliminating downloads, conversions, and duplicate files, LVC ensures consistency and saves staff from unnecessary post-hearing tasks.

Glendale's Workflow Transformed

Before adopting LVC, clerks in Glendale had to download and back up each Zoom recording to the courthouse's "R" drive - a manual process that added stress and slowed workflow.

Devin McMillion explained: "Clerks were required to download and back up each Zoom recording ... creating yet another manual step that added to their workload." Since deploying LVC, that entire step has been eliminated. "Clerks no longer have to spend extra time downloading and backing up recordings, since everything is captured automatically within Liberty's recorder."

The result is fewer errors, less repetitive work, and more time for clerks to focus on higher-value support for judges and case flow.

Problem #3: In-Room Audio and Video Integration

Why Remote Voices Go Unheard

One of the recurring challenges in hybrid hearings is poor audio distribution in the courtroom. On general-purpose platforms, remote participants' voices often play only through a laptop or small bench speaker, making it difficult for everyone present to hear clearly. This not only frustrates participants but also undermines the sense of professionalism and formality that court proceedings demand. And in some setups can lead to chronic echo.

How LVC Delivers Clear, Courtroom-Quality Audio

Liberty Virtual Courtroom integrates directly with existing courtroom microphones, speakers, and Liberty Court Recorder. Remote participant audio is routed through the courtroom's main digital signal processor (DSP) - the same system used for in-room proceedings - ensuring that every voice is heard with clarity and without echo. This design elevates the formality of the hearing, maintains continuity with existing AV infrastructure, and reinforces courtroom professionalism.

Better Sound, Smoother Hearings in Glendale

Devin McMillion highlighted the unexpected impact this had on Glendale: "With Liberty Virtual Courtroom, participant audio plays through the courtroom's main speakers, rather than just external speakers at the judge's bench. This is a significant improvement, providing a more professional experience and making it easier for everyone in the courtroom to hear clearly." The shift not only improved audibility but also contributed to smoother proceedings and a more formal atmosphere in the courtroom - a detail that judges and staff quickly came to value.

Problem #4: Public Access and Participant Confusion

The Confusion Behind Virtual Access

NCSC studies highlight that participant confusion is one of the leading causes of delay in virtual hearings. Multiple meeting links, passwords, and unclear access points often require clerks to spend valuable time walking participants through the connection process. Language access is another barrier: courts serving multilingual communities need to provide instructions and prompts in multiple languages, something most generic platforms don't support.

How LVC Makes Access Simple

Liberty Virtual Courtroom simplifies participant access with persistent lobby links tied to each courtroom. Links do not need to be regenerated when schedules change, reducing confusion and lost time. Additionally, LVC provides multilingual access, with all links, prompts, and voice instructions available in English, Spanish, and French. This ensures equitable access for participants and minimizes the need for staff intervention.

Glendale's Participants Join With Ease

According to Devin McMillion: "Since participants can either use a provided link or access the platform directly from our website, joining Liberty is much smoother and more straightforward. This reduces confusion and delays, minimizes the need for staff to provide technical support, and ensures that hearings start on time."

Conclusions

For Glendale, Liberty Virtual Courtroom turned persistent challenges into measurable improvements. Login conflicts no longer derail hearings, recordings save automatically without clerical overhead, participant audio reaches the full courtroom, and public access is simple and reliable.

The result is more than convenience - it's a courtroom environment that feels professional, efficient, and prepared. Judges and staff focus on justice instead of technology, and participants experience smoother, more accessible proceedings.

Glendale's experience underscores a clear truth: while general-purpose conferencing platforms may suffice for office meetings, courts require a purpose-built solution. Liberty Virtual Courtroom delivers that focus, enabling courts to reduce disruption, simplify workflows, and keep cases moving forward with confidence.

For inquiries related to the Glendale City Court's implementation, contact Devin McMillion at: demcmillion@courts.az.gov

¹National Center for State Courts (NCSC). Remote Hearings and Access to Justice: Lessons Learned from the Pandemic, 2021.

Contact Liberty Recording for more Information about the Liberty Virtual Courtroom and how it can enhance your courtroom's operational workflow.