> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.thymia.ai/llms.txt.
> For full documentation content, see https://docs.thymia.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.thymia.ai/_mcp/server.
# thymia documentation
## The health and safety intelligence layer for voice
thymia extracts clinically validated health and wellbeing signals from
voice — not transcription, not sentiment analysis, but the biological
signal contained in sound, made actionable.
Voice sits at the intersection of five major biological systems —
respiratory, neurological, cardiovascular, metabolic, and
musculoskeletal. Change any one of them, and the voice changes with it.
Every voice contains thousands of measurable patterns: subtle variations
in pitch, rhythm, pauses, and tone. thymia calls the smallest distinct
units **neural morphemes™** — the fundamental building blocks of speech that
carry meaning beyond words.
thymia's foundational models identify these **neural morphemes™** in real
time, then combine them into biomarkers — specific signatures that
reliably indicate health and wellbeing states. Just as a doctor
recognises symptoms that together suggest a diagnosis, our models
recognise morpheme patterns that together reveal emotional, mental, and
physiological states. From just 15 seconds of speech, processed in
real time.
| Signal | Examples |
| ----------------------- | ------------------------------------------------------------ |
| **Acoustic features** | Pitch variation, speech rate, pauses, vocal tremor, loudness |
| **Linguistic patterns** | Word choice, sentence structure, semantic content |
| **Temporal dynamics** | Response timing, speech rhythm, prosody changes |
All capabilities are accessible through a REST API, designed to
integrate into any platform or workflow that handles voice.
## Choose your integration
thymia integrates into any platform or workflow that handles voice.
Whether you are building a remote patient monitoring tool, enriching an
existing voice agent, or embedding mental health screening into a
clinical pathway, thymia delivers biomarker-grade intelligence from
seconds of natural speech.
### thymia API
Supply voice recordings directly from your infrastructure.
Your backend creates a model run, uploads the recording, and polls for
results. Full control over the recording experience and user journey
from end to end.
### Sentinel
Real-time voice safety and wellbeing monitoring for AI agents.
Stream audio and transcripts, run safety policies, and get
actionable results — all without storing recordings.
## Choose your model
### Helios
#### Wellbeing and safety monitoring
Wellbeing monitoring from live voice. Detects distress, stress,
fatigue, low self-esteem, and burnout in real time — across
human and voice agent interactions — for healthcare, pharma,
and safety-critical industries.
### Apollo Clinical
#### Clinical-grade health detection
Voice-based depression and anxiety assessment covering all DSM-V
criteria with disorder-level results and granular symptom scores.
Apollo is a regulated medical device intended for qualified
healthcare professionals only.
***
