--- source_path: "reference/overview.md" canonical_url: "https://doc.sensory.com/tnl/7.8/reference/overview/" --- # Overview This section provides a brief overview of this SDK: Features supported by [variant](https://doc.sensory.com/tnl/7.8/reference/overview.md#variants), development host [requirements](https://doc.sensory.com/tnl/7.8/reference/overview.md#requirements), [supported target platforms](https://doc.sensory.com/tnl/7.8/reference/overview.md#supported-target-platforms), `snsr` [model](https://doc.sensory.com/tnl/7.8/reference/overview.md#ref-models) files, command-line [tools](https://doc.sensory.com/tnl/7.8/reference/overview.md#ref-tools), and the software [license keys](https://doc.sensory.com/tnl/7.8/reference/overview.md#license-keys) used to control library features. ## Variants The TrulyHandsfree, TrulyNatural (Lite), and TrulyNatural STT SDKs differ **only** in the types of models they support. The APIs, model formats, tools, etc. are identical. TrulyNatural STT is a strict superset of TrulyNatural (Lite), which in turn is a strict superset of TrulyHandsfree. **[TrulyNatural STT][tnl-stt]:** * [x] Speech-To-Text with transformers and compressed language models. * [x] Recognition hypotheses include punctuation and capitalization. * [x] Machine-learned NLU for intent and entity identification. * [x] Generative language models. * [x] **Sensory has models available for 35 languages**, each in multiple sizes (for best accuracy given a CPU cycle budget). Contact your account representative or [Sensory Sales](https://doc.sensory.com/tnl/7.8/contact.md#sales) for details. * [x] _Includes [Open Source software](https://doc.sensory.com/tnl/7.8/licenses/oss.md#open-source-licenses)._ * [x] Features available in TrulyNatural STT only are flagged with _(STT only)_ **[TrulyNatural Lite][tnl-lite]:** * [x] Phonemic acoustic models with FST vocabulary decoding. * [x] [Grammar-based](https://doc.sensory.com/tnl/7.8/models/types/lvcsr.md#grammar-based-recognition) medium vocabulary command and control. * [x] Grammar-based NLU for intent and entity identification. * [x] Tools to build recognizers from grammars or phrase lists. * [x] API to build or augment recognizers at runtime. * [x] Runs [VoiceHub](https://doc.sensory.com/tnl/7.8/reference/voicehub.md#voicehub) "large natural language vocabulary" models. * [x] Support for devices with limited RAM (< 1 MiB) and CPU (< 500 MHz). * [x] _No third-party or Open Source software._ * [x] Features available in TrulyNatural (Lite and STT) only are flagged with _(TrulyNatural only)_ **[TrulyHandsfree][thf]:** * [x] [Fixed](https://doc.sensory.com/tnl/7.8/models/types/wake-word.md#wake-word-type), [enrolled](https://doc.sensory.com/tnl/7.8/models/types/enroll.md#enroll-type) and [adapting](https://doc.sensory.com/tnl/7.8/models/types/ca.md#ca-type) wake words. * [x] Command sets, which are keyword spotter recognizers for multiple (up to twenty) active phrases. * [x] [VAD](https://doc.sensory.com/tnl/7.8/api/setting-keys/values.md#vad). * [x] [Command-line tools](https://doc.sensory.com/tnl/7.8/tools/index.md#command-line-tools) to enroll and evaluate wake word models, and to convert wake word models into Sensory's [THF Micro][] DSP format. * [x] Runs [VoiceHub](https://doc.sensory.com/tnl/7.8/reference/voicehub.md#voicehub) "wake word" and "simple commands" projects. * [x] _No third-party or Open Source software._ ## Requirements For development, you'll need: - macOS, x86_64 Linux, or Windows (version 10 or later, [Microsoft Visual Studio][msvc] 2022) development machine. - iOS: [Xcode] 26.5 or later. - Java: [Java JDK][jdk] 11 through 21. - Android: [Android Studio Panda][as] 2025.3.4 or later. [API level 21][api-levels] or later. **Verified with:** TrulyNatural SDK 7.9.0-pre.0 was verified against **Xcode 26.5** and **Android Studio Panda 4 | 2025.3.4 Patch 1**. Newer point releases are expected to work but are not part of the release-test matrix. Models require audio encoded as 16-bit LPCM and sampled at 16 kHz. For optimal recognition accuracy, ensure that the dynamic range of the input audio spans **at least** 12 bits (-24 [dBFS][] peak-to-peak, sample values from -2048 to 2047) and that no clipping is present. ## Supported target platforms TrulyHandsfree and TrulyNatural run on hundreds of different operating systems and CPU combinations. This distribution includes a subset of these in _~/Sensory/TrulyNaturalSDK/7.9.0-pre.0/lib/_. See the `README` files in the platform subdirectories for additional details, such as the toolchain and compiler flags used to build the library. TrulyNatural STT is available for Android, iOS on `arm64` and `arm64e`, macOS, Linux on `x86_64`, `aarch64`, and `arm`, and Windows on `x86_64`. [Contact](https://doc.sensory.com/tnl/7.8/contact.md#contact) Sensory if your target platform isn't listed. Platform { data-sort-default }| STT support| Note :-----------------------------|:----------:|:---- `aarch64-linux-gnu` | • yes | [GLIBC][] >= 2.33 `arm-linux-gnueabi` | • no | [GLIBC][] >= 2.17 `arm-linux-gnueabihf` | • yes | [GLIBC][] >= 2.33 `arm-none-eabi` | • no `arm-none-eabihf` | • no `arm-none-eabihf-ethosu` | • no `armv6-linux-gnueabihf` | • no | [GLIBC][] >= 2.17 `i686-linux-gnu` | • no | [GLIBC][] >= 2.17 `ios` | • yes | 64-bit only `android` | • yes | [API level][api-levels] >= 21 `macos` | • yes `mipsel-buildroot-linux-uclibc` | • no `mipsel-openwrt-linux-musl` | • no `x86_64-linux-gnu` | • yes | [GLIBC][] >= 2.17 `x86_64-windows-msvc` | • yes | Requires [MSVC Runtime][] 2022 *Included target platform libraries* ## Models TrulyNatural SDK `.snsr` files include all the models and settings required for a task, and a flow graph that defines the behavior. A task can be as simple as a single-phrase [wake word](https://doc.sensory.com/tnl/7.8/models/types/wake-word.md#wake-word-type), or something more complicated such as wake word followed by a VAD and an STT recognizer that transcribes the detected speech segment. If you're just interested in the final recognition results, the code required to run these two examples is identical. This distribution includes sample [models](https://doc.sensory.com/tnl/7.8/models/index.md#models) and [templates](https://doc.sensory.com/tnl/7.8/models/index.md#templates) used to add additional behaviors to these. ## Tools The _~/Sensory/TrulyNaturalSDK/7.9.0-pre.0/bin/_ directory contains a number of [command-line tools](https://doc.sensory.com/tnl/7.8/tools/index.md#command-line-tools). These evaluate models, compose new models, modify settings, enroll wake words, convert wake word models to [THF Micro][] DSP format, and diagnose audio recording quality. These utilities are compiled for the development host. You can [compile these from source](https://doc.sensory.com/tnl/7.8/api/sample/c/index.md#c-examples) for other platforms. ## License keys The TrulyNatural SDK installer embeds the license key entered on the "Product Licensing" page in the libraries and tools it installs. All applications that link against these libraries include this license key. Keys include the SDK licensee name. License keys control access to specific SDK features, target platforms, CPU architectures, and to specify an expiration date for access. Model files also include license keys. These are validated upon loading. License keys fall into two broad categories: _development_ ones which either expire at some future date or limit use, and _production_ keys which do not expire and do not have usage limits. You can use the [LICENSE](https://doc.sensory.com/tnl/7.8/api/library-config.md#config_license) option to apply an updated license key with the [configuration](https://doc.sensory.com/tnl/7.8/api/library-config.md#config) API at runtime. **Warning:** Do _not_ use development / expiring keys in shipping products. These will stop working when the keys expire. [Contact](https://doc.sensory.com/tnl/7.8/contact.md#contact) Sensory to obtain production-ready libraries and models. **Also see these related items:** [license-exp-date](https://doc.sensory.com/tnl/7.8/api/setting-keys/library-information.md#license-exp-date), [license-exp-message](https://doc.sensory.com/tnl/7.8/api/setting-keys/library-information.md#license-exp-message), [license-exp-warn](https://doc.sensory.com/tnl/7.8/api/setting-keys/library-information.md#license-exp-warn), [model-license-exp-date](https://doc.sensory.com/tnl/7.8/api/setting-keys/runtime.md#model-license-exp-date), [model-license-exp-message](https://doc.sensory.com/tnl/7.8/api/setting-keys/runtime.md#model-license-exp-message), [model-license-exp-warn](https://doc.sensory.com/tnl/7.8/api/setting-keys/runtime.md#model-license-exp-warn), [LICENSE](https://doc.sensory.com/tnl/7.8/api/library-config.md#config_license), [LICENSE_NOT_VALID](https://doc.sensory.com/tnl/7.8/api/inference.md#rc), [LICENSE_LIMIT_EXCEEDED](https://doc.sensory.com/tnl/7.8/api/inference.md#rc), [LICENSE_OVERRIDE_NOT_SUPPORTED](https://doc.sensory.com/tnl/7.8/api/inference.md#rc_license_override_not_supported), [LICENSE_OVERRIDE_NOT_ENABLED](https://doc.sensory.com/tnl/7.8/api/inference.md#rc_license_override_not_enabled) [api-levels]: https://en.wikipedia.org/wiki/Android_version_history "Android version history and API levels" [as]: https://developer.android.com/studio/index.html "Android Studio" [dBFS]: https://en.wikipedia.org/wiki/DBFS "Decibels relative to full scale" [GLIBC]: https://sourceware.org/glibc/wiki/Glibc%20Timeline "GNU C Library Release Timeline" [jdk]: https://adoptium.net "Java Development Kit" [msvc]: https://visualstudio.com/ "Microsoft Visual Studio" [MSVC Runtime]: https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170#visual-studio-2015-2017-2019-and-2022 "Microsoft Visual C++ Redistributable" [thf]: https://www.sensory.com/wake-word/ "Low Power Wake Words & Phrase Recognition Engine" [THF Micro]: https://doc.sensory.com/thf-micro/ "THF Micro documentation" [tnl-lite]: https://www.sensory.com/natural-language-understanding/ "Large Vocabulary Continuous Speech Recognition (LVCSR) with Dynamic Natural Language Understanding" [tnl-stt]: https://www.sensory.com/embedded-speech-to-text/ "Embedded Speech To Text" *[API]: Application Programming Interface *[FST]: Finite-State Transducer *[LPCM]: Linear pulse-code modulation *[LVCSR]: Large Vocabulary Continuous Speech Recognition model, feed-forward neural net acoustic model with FST decoder *[NLU]: Natural Language Understanding model *[OSS]: Open-source software *[RAM]: Random Access Memory *[SDK]: Software Development Kit *[STT]: Speech To Text: transformers with language model and CTC decoding *[THF]: TrulyHandsfree, Sensory's wake word and command recognition technology *[TNL]: TrulyNatural, Sensory's large-vocabulary speech recognition technology *[VAD]: Voice Activity Detector