Voicing the Data: Partnering with ElevenLabs to Make Health Equity Guides Accessible
Local Kine AI · October 2024
In October 2024, the Health Equity Tracker team was accepted into ElevenLabs' Impact Partner Program, which gave us a complimentary year of their Creator plan — 100,000 voice-AI credits a month — in exchange for featuring their logo and tagging them once on social media. We used it to add narrated audio to our "How to Use the Data" guide series, starting with a Gun Violence-focused walkthrough of HET's core visualizations.
QE Rationale
Counts toward Fundamentals of Educational Technology Leadership — using AI voice technology to make HET's how-to guidance accessible across different learning and processing styles is the same kind of tech-enabled access work reflected in the Claim What Is Yours entry.
Role: Sole point of contact for the ElevenLabs partnership — wrote the narration scripts, selected which visualizations to feature, and handled the technical integration end-to-end, including applying to the Impact Partner Program and managing onboarding.
Tools: ElevenLabs (voice AI, Creator plan)
Timeline: October 2024 (partnership secured); ongoing narration work for HET's guide series
The Problem
- A content pipeline that had outgrown my own bandwidth. I'd been producing a growing library of YouTube Shorts and TikToks for HET, but our team had no dedicated volunteer pipeline for voiceover work, and narrating everything myself wasn't sustainable stacked on top of everything else already stretched thin.
- An accessibility gap in HET's own guide series. The "How to Use the Data" guides existed as text-and-visual walkthroughs only — no format for users who process information better by ear, have a visual impairment, or want to follow along while doing something else.
- A representation question, once the tool was in hand. Once narration became technically possible, the content being narrated — Georgia gun-violence data that disproportionately affects Black communities, produced at an HBCU, funded by a foundation focused on those same communities — raised the question of whose voice should be telling that story.
Design Process
Getting there through a colleague's referral, not a cold search Ben Hammond flagged ElevenLabs after watching me try to keep up with narrating HET's growing short-form video library myself, on a team too small to spare a dedicated voiceover volunteer.
Applying for tooling built for exactly this constraint ElevenLabs' Impact Partner Program gives free voice-AI access to nonprofits, accessibility-focused organizations, and educators. I applied and secured a complimentary year of their Creator plan — 100,000 voice-AI credits a month — in exchange for a logo credit and one social tag.
Choosing content that made the case concretely I started with a Gun Violence–focused walkthrough covering seven of HET's core visualization types — rate choropleth map, rates-over-time chart, rate bar chart, unknown-demographic choropleth map, relative inequity chart, population-vs-distribution stacked bar chart, and breakdown summary table — using real Georgia data (a 43-per-100,000 gun homicide rate for Black non-Hispanic men) to make each visualization concrete rather than abstract.
Choosing who tells the story, not just what it says ElevenLabs offers a range of Black-voiced options, and I chose from among them deliberately for this series: the data being narrated is Georgia gun-violence data that disproportionately affects Black communities, Morehouse School of Medicine — where I work — is an HBCU, and Annie E. Casey Foundation's funding for this work is aimed at the same communities the data describes. Matching who narrates the data to who the data is about wasn't a footnote — it was part of the design.
Writing for the ear, not just reading text aloud Each narrated segment closes with an invitation to bring the data to local officials and community leaders — scripted deliberately for listening, not repurposed verbatim from the guide's written text.
Reflection
Accessibility is core to how HET approaches data: the tracker already treats missing or mislabeled data as its own kind of health-equity issue, and audio narration extends that same logic to how people take in the data in the first place.
This partnership started with a referral, not a cold application. I'd been producing a growing library of YouTube Shorts and TikToks for HET, and our team was too small to keep a dedicated volunteer pipeline for voiceover work — narrating everything myself wasn't sustainable on top of everything else already stretched thin. Ben Hammond flagged ElevenLabs as a fit, and the Impact Partner Program's free year of Creator-plan access solved exactly that bottleneck, starting with the Gun Violence–focused series Annie E. Casey Foundation had funded.
The voice selection wasn't incidental either. I chose from ElevenLabs' Black-voiced options deliberately for this series: the data being narrated disproportionately affects Black communities, Morehouse School of Medicine is an HBCU, and Annie E. Casey Foundation's funding for this work is aimed at those same communities. Matching who narrates the data to who the data is about wasn't a footnote — it was part of the design.
Outcomes
- The first AI-narrated entry in HET's "How to Use the Data" series — a fully accessible, audio-narrated Gun Violence walkthrough covering seven visualization types.
- A year of complimentary ElevenLabs Creator-plan access (100,000 voice-AI credits a month) secured through the Impact Partner Program, in exchange for a logo credit and one social tag.
- A deliberate, mission-aligned narration choice — Black voice talent selected to match the communities represented in the data and centered by the funding behind the work.
- Full use of the monthly credit allotment, with hands-on familiarity built up across ElevenLabs' voice range for future guide entries.
Related work
Building a Zero-Cost Grant Monitoring Microservice
With our three team roles confirmed funded through FY27, I began transitioning into a grants-facing capacity alongside my UX engineering responsibilities, taking on the early infrastructure work that a dedicated grants professional would otherwise own.
Rather than monitoring dozens of foundation websites manually or investing in a grant database subscription that tracked historical awards rather than live open calls, I scoped and built Grant Watchdog: a lightweight automation tool that watches the live web pages of curated funder targets for changes, flags potential new opportunities, and generates a plain-language report the whole team can read.
Social Responsibilities Round Table Talk
From Data to Action: How Open-Source Health Data Platforms Democratize Research and Empower Community Advocacy
Open-source platforms like HET democratize research, transforming health equity from an academic concept to a community tool
Claim What Is Yours: A Trauma-Informed Content System for a High-Stakes Writing Task
Claim What Is Yours was a personal initiative I built to address a gap I'd lived through directly: veterans navigating VA disability claims — particularly for conditions tied to military sexual trauma — face a writing task that is procedurally demanding and, for many, close to impossible to approach directly. I designed a four-part content system (a free introductory guide plus a core guide with two companion modules) to walk survivors from "I don't know where to start" to a completed claim package, using AI tools as a structured writing partner along the way.
Description The core design problem wasn't information delivery — the VA's process is documented; it's the access gap between knowing the steps and being able to sit down and do them. I addressed that in a few specific ways: Staged disclosure architecture. Rather than asking a reader to write their most difficult account first, I sequenced the material so the hardest writing task (the formal MST stressor statement) comes after three lower-stakes "shadow work" exercises — third-person narration, a before/after contrast, and a behavioral-markers inventory — each one building material the reader can carry forward into the harder document, so no one starts at the hardest point. Structured AI-prompting as a writing scaffold. I wrote reusable, fill-in-the-blank prompt templates for every major document in the process (personal statements, nexus letter requests, buddy letter asks), each engineered to produce output in the reader's own voice rather than a generic or clinical one, and each paired with explicit guidance on what to check in the output before using it. Explicit safety and data-literacy guidance. Because the audience would be using AI tools for the first time, often around highly sensitive material, I included direct instruction on what not to disclose to an AI platform, how to evaluate a tool's data practices, and clear crisis-line signposting throughout — treating tool literacy as part of the content's job, not an afterthought. A tiered information structure. Free → core guide → bonus modules, so a reader in crisis could access something immediately useful at zero cost, with a deeper system available for those ready to go further.
Let's connect