Spencer Wright

AI Audio Fix for Embark

Developed an AI audio feature that resolved complaints and ensured accuracy in 60+ languages.

Product

Embark App

Team

1 Designer

1 Project Manager

1 Developer

Role

Design lead

Timeline

4 weeks

Overview

Imagine learning a new language—and going through the work to fixing a typo in the apps content, only to hear the audio still say the wrong word. This was a common issue in Embark, a language-learning app for Mormon missionaries learning to speak in over 60 languages. 

To adress this problem I designed an AI-powered audio tool that automatically updates mismatched clips or lets users create a new one with a single tap. This reduced user complaints and improved audio accuracy.

My impact

Audio Complaints Dropped Significantly

User-reported audio issues decreased significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

Background

Problem

In some less-reviewed languages, learners often corrected typos in words and phrases. But even after fixing the text, the original audio stayed the same. This mismatch confused users and led to a spike in support tickets.

  • Audio and text fell out of sync, making pronunciation unreliable.
  • There was no way as a user to change a word’s audio

Goal

Create a way to keep audio and text in sync—even after edits.

Research

Finding a related problem

I reviewed all audio-related support emails and Jira tickets and found a second, related issue:

Poor audio quality

  • Users frequently reported low-quality recordings in some languages.
  • The content team was re-recording audio manually, but this was slow and hard to scale for Embark’s 60+ supported languages.

Opportunity

Both issues pointed to the same need: fast, scalable audio generation that didn’t rely on human re‑recording.

Brainstorming

Exploring options

Before committing to a solution, we considered multiple ways to improve audio accuracy after text edits:

Idea 1

User records their own audio

Empowers learners

Risk of mispronunciation reinforces habits.

Idea 2

AI generated audio (Selected)

Fast, consistent, supports 60+ languages

Needed quality validation

After team discussions, I partnered with a developer to test AI audio across multiple languages. It delivered fast, high-quality results without needing manual recordings—making it the clear choice over user-recorded audio.

Design

Auto-generate audio after edits

After choosing the AI approach, I designed a way to auto-generate audio when a word was edited, keeping audio and text in sync.

Audio generated automatically.

Audio Card

To address the audio quality issue, I also introduced an Audio Card to the word-edit screen. It allowed users to

  1. Preview the current audio,
  2. Generate new audio,
  3. Revert to the original if needed.

Generating new audio

Testing

Usability test

I ran a usability test with 5 missionaries at the MTC. Each participant went through the full process of editing a word and generating new audio.

Test results

Successful Completion

All 5 successfully completed the tasks without confusion or errors.

Validated Solution

All said it clearly fixed the mismatch issue and would be a major improvement.

Outcome

After successful testing, we launched the AI audio fix across supported languages. The result: cleaner experiences, fewer complaints, and better pronunciation for everyone.

Results

Audio Complaints Dropped Significantly

User-reported audio issues dropped significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

Say hi

LinkedIn

© 2025 Spencer Wright

SW

Work
Resume
Contact

AI Audio Fix for Embark

Developed an AI audio feature that resolved complaints and ensured accuracy in 60+ languages.

Product

Embark App

Team

1 Designer

1 Project Manager

1 Developer

Role

Design lead

Timeline

4 weeks

Overview

Imagine learning a new language—and going through the work to fixing a typo in the apps content, only to hear the audio still say the wrong word. This was a common issue in Embark, a language-learning app for Mormon missionaries learning to speak in over 60 languages. 

To adress this problem I designed an AI-powered audio tool that automatically updates mismatched clips or lets users create a new one with a single tap. This reduced user complaints and improved audio accuracy.

My impact

Audio Complaints Dropped Significantly

User-reported audio issues decreased significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

Background

Problem

In some less-reviewed languages, learners often corrected typos in words and phrases. But even after fixing the text, the original audio stayed the same. This mismatch confused users and led to a spike in support tickets.

  • Audio and text fell out of sync, making pronunciation unreliable.
  • There was no way as a user to change a word’s audio

Goal

Create a way to keep audio and text in sync—even after edits.

Research

Finding a related problem

I reviewed all audio-related support emails and Jira tickets and found a second, related issue:

Poor audio quality

  • Users frequently reported low-quality recordings in some languages.
  • The content team was re-recording audio manually, but this was slow and hard to scale for Embark’s 60+ supported languages.

Opportunity

Both issues pointed to the same need: fast, scalable audio generation that didn’t rely on human re‑recording.

Brainstorming

Exploring options

Before committing to a solution, we considered multiple ways to improve audio accuracy after text edits:

Idea 1

User records their own audio

Empowers learners

Risk of mispronunciation reinforces habits.

Idea 2

AI generated audio (Selected)

Fast, consistent, supports 60+ languages

Needed quality validation

After team discussions, I partnered with a developer to test AI audio across multiple languages. It delivered fast, high-quality results without needing manual recordings—making it the clear choice over user-recorded audio.

Design

Auto-generate audio after edits

After choosing the AI approach, I designed a way to auto-generate audio when a word was edited, keeping audio and text in sync.

Audio generated automatically.

Audio Card

To address the audio quality issue, I also introduced an Audio Card to the word-edit screen. It allowed users to

  1. Preview the current audio,
  2. Generate new audio,
  3. Revert to the original if needed.

Generating new audio

Testing

Usability test

I ran a usability test with 5 missionaries at the MTC. Each participant went through the full process of editing a word and generating new audio.

Test results

Successful Completion

All 5 successfully completed the tasks without confusion or errors.

Validated Solution

All said it clearly fixed the mismatch issue and would be a major improvement.

Outcome

After successful testing, we launched the AI audio fix across supported languages. The result: cleaner experiences, fewer complaints, and better pronunciation for everyone.

Results

Audio Complaints Dropped Significantly

User-reported audio issues dropped significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

© 2025 Spencer Wright

Say hi

LinkedIn

SW

Work

Resume
Contact

AI Audio Fix for Embark

Developed an AI audio feature that resolved complaints and ensured accuracy in 60+ languages.

Product

Embark App

Team

1 Designer

1 Project Manager

1 Developer

Role

Design lead

Timeline

4 weeks

Overview

Imagine learning a new language—and going through the work to fixing a typo in the apps content, only to hear the audio still say the wrong word. This was a common issue in Embark, a language-learning app for Mormon missionaries learning to speak in over 60 languages. 

To adress this problem I designed an AI-powered audio tool that automatically updates mismatched clips or lets users create a new one with a single tap. This reduced user complaints and improved audio accuracy.

My impact

Audio Complaints Dropped Significantly

User-reported audio issues decreased significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

Background

Problem

In some less-reviewed languages, learners often corrected typos in words and phrases. But even after fixing the text, the original audio stayed the same. This mismatch confused users and led to a spike in support tickets.

  • Audio and text fell out of sync, making pronunciation unreliable.
  • There was no way as a user to change a word’s audio

Goal

Create a way to keep audio and text in sync—even after edits.

Research

Finding a related problem

I reviewed all audio-related support emails and Jira tickets and found a second, related issue:

Poor audio quality

  • Users frequently reported low-quality recordings in some languages.
  • The content team was re-recording audio manually, but this was slow and hard to scale for Embark’s 60+ supported languages.

Opportunity

Both issues pointed to the same need: fast, scalable audio generation that didn’t rely on human re‑recording.

Brainstorming

Exploring options

Before committing to a solution, we considered multiple ways to improve audio accuracy after text edits:

Idea 1

User records their own audio

Empowers learners

Risk of mispronunciation reinforces habits.

Idea 2

AI generated audio (Selected)

Fast, consistent, supports 60+ languages

Needed quality validation

After team discussions, I partnered with a developer to test AI audio across multiple languages. It delivered fast, high-quality results without needing manual recordings—making it the clear choice over user-recorded audio.

Design

Auto-generate audio after edits

After choosing the AI approach, I designed a way to auto-generate audio when a word was edited, keeping audio and text in sync.

Audio generated automatically.

Audio Card

To address the audio quality issue, I also introduced an Audio Card to the word-edit screen. It allowed users to

  1. Preview the current audio,
  2. Generate new audio,
  3. Revert to the original if needed.

Generating new audio

Testing

Usability test

I ran a usability test with 5 missionaries at the MTC. Each participant went through the full process of editing a word and generating new audio.

Test results

Successful Completion

All 5 successfully completed the tasks without confusion or errors.

Validated Solution

All said it clearly fixed the mismatch issue and would be a major improvement.

Outcome

After successful testing, we launched the AI audio fix across supported languages. The result: cleaner experiences, fewer complaints, and better pronunciation for everyone.

Results

Audio Complaints Dropped Significantly

User-reported audio issues dropped significantly, boosting trust in the app.

Accurate Pronunciation

AI ensures text and audio always match—across 60+ languages.

© 2025 Spencer Wright

Say hi

LinkedIn