---
source_path: "models/types/index.md"
canonical_url: "https://doc.sensory.com/tnl/7.8/models/types/"
---

# Model types

The [type](https://doc.sensory.com/tnl/7.8/api/setting-keys/configuration.md#task-type) of a model specifies the runtime behavior: what it does, which [setting keys](https://doc.sensory.com/tnl/7.8/api/setting-keys/index.md#setting-keys) it supports, and when it invokes [event](https://doc.sensory.com/tnl/7.8/api/setting-keys/events.md#events) callbacks.

These SDKs support both [fundamental](https://doc.sensory.com/tnl/7.8/models/types/index.md#fundamental-models) and [composed](https://doc.sensory.com/tnl/7.8/models/types/index.md#composed-models) model types. Fundamental types include wake words, adapting wake words, models that create wake words through user enrollment, VAD, LVCSR, and STT. Templates add features by composition, combining multiple fundamental models into one.

The TrulyHandsfree SDK supports all wake word, wake word enrollment, and VAD models.
TrulyNatural (Lite) includes TrulyHandsfree and support for LVCSR. TrulyNatural STT includes TrulyNatural (Lite) and adds speech to text.

## Fundamental models

[Wake word](https://doc.sensory.com/tnl/7.8/models/types/wake-word.md#wake-word-type)

- Fixed and enrolled wake words, and keyword spotted command sets.

[Adapting wake word](https://doc.sensory.com/tnl/7.8/models/types/ca.md#ca-type)

- Fixed wake word models that continuously adapt to speakers' voices to improve false-accept rates.

[Wake word enrollment](https://doc.sensory.com/tnl/7.8/models/types/enroll.md#enroll-type)

- Adapts fixed (EFT) and user-defined (UDT) wake words to speakers' voices, creating [wake word](https://doc.sensory.com/tnl/7.8/models/types/wake-word.md#wake-word-type) models specific to these speakers.

[VAD](https://doc.sensory.com/tnl/7.8/models/types/vad.md#vad-type)

- Finds the start- and endpoints of speech segments in a stream of audio data.

[LVCSR](https://doc.sensory.com/tnl/7.8/models/types/lvcsr.md#lvcsr-type) _(TrulyNatural only)_

- These recognizers use a phonetic acoustic model and an FST vocabulary decoder. They are suitable for small to medium vocabulary tasks, but not for audio transcription

[STT](https://doc.sensory.com/tnl/7.8/models/types/stt.md#stt-type) _(STT only)_

- Audio transcription with transformers.

## Composed models

[Templates](https://doc.sensory.com/tnl/7.8/models/tpl/index.md#template-type) add behavior to the fundamental model types listed above. Use these, for example, to create a single model that waits for a keyword, runs  a VAD, and then recognizes the segmented speech with an STT recognizer. This composed model uses the same API as a simple wake word and does not require application code changes.

<!-- Abbreviation definitions from includes/abbreviations.md -->
*[API]: Application Programming Interface
*[EFT]: Enrolled Fixed Trigger: fixed wake words adapted to a speaker to improve accuracy
*[FST]: Finite-State Transducer
*[LVCSR]: Large Vocabulary Continuous Speech Recognition model, feed-forward neural net acoustic model with FST decoder
*[SDK]: Software Development Kit
*[STT]: Speech To Text: transformers with language model and CTC decoding
*[TNL]: TrulyNatural, Sensory's large-vocabulary speech recognition technology
*[UDT]: User-Defined Trigger: enrolled wake words and command sets
*[VAD]: Voice Activity Detector