The investigators previously demonstrated that voice changes are common in patients with Laryngotracheal Stenosis (LTS), and patients typically report an improvement in voice outcomes following endoscopic dilation. Recently, NIH based programs such as a Bridge to Artificial Intelligence (Bridge2AI) have highlighted the use of artificial intelligence to identify acoustic biomarkers of disease. Therefore, the investigators hypothesize that progression of LTS scar can be quantified using acoustic measurements and machine learning. The goal of this clinical trial is to remotely monitor patient voice quality in an effort to determine if regularly performed voice recordings can be used as a diagnostic tool in order to predict the need for dilation procedures. The investigators feel that successful use of remote voice recording technology with algorithmic analysis will improve patient quality of life.

Inclusion Criteria:

• Current diagnosis of laryngotracheal stenosis
• Patient age 18 - 80 years old
• Eastern Cooperative Oncology Group (ECOG) performance status of 0 - 1
• The patient must be able to comprehend and have signed the informed consent.
• The patient must have documentation of their date of laryngotracheal stenosis diagnosis and prior medical/surgical history.

Exclusion Criteria:

• Inability to use the app associated with the study.
• Comorbid laryngeal or glottic disease
• Concurrent neurological disease which may impact voice use (such as tremor, parkinsonism, laryngeal dystonia)

Individuals with idiopathic subglottic stenosis