Your first program¶

• A C compiler and CMake 3.10 or later (Linux, macOS, or Windows).
• A microphone for live audio.
• A phrase-spot model file, for example the voice genie model at $HOME/Sensory/TrulyNaturalSDK/7.8.0-pre.2/model/spot-voicegenie-enUS-6.5.1-m.snsr.

• JDK 17 or later and Gradle 8.0 or later (or use a Gradle wrapper).
• A microphone (Java Audio capture via fromAudioDevice).
• A phrase-spot .snsr file (same voice genie model path as the C tab).

• Python 3.10 or later and uv (or pip install the platform wheel).
• A microphone (Stream.from_audio_device() — see fromAudioDevice).
• A phrase-spot .snsr file (same voice genie model path as the C tab).

• Android Studio or a command-line Android SDK install; device or emulator with microphone support.
• To try the sample on this page you do not need to change sample source — only build and run snsr-debug.

• Xcode on macOS and a device or simulator with microphone access.
• To try the sample on this page you do not need to change sample source — only open and run PhraseSpot.

Create first-spot.c with:

#include <snsr.h>
#include <stdio.h>
#include <stdlib.h>

static SnsrRC
resultEvent(SnsrSession s, const char *key, void *privateData)
{
  const char *phrase;
  SnsrRC r;

  r = snsrGetString(s, SNSR_RES_TEXT, &phrase);
  if (r != SNSR_RC_OK)
    return r;
  printf("Spotted \"%s\".\n", phrase);
  return SNSR_RC_STOP;
}

int
main(int argc, char *argv[])
{
  SnsrRC r;
  SnsrSession s;

  if (argc != 2) {
    fprintf(stderr, "usage: %s spotter-model\n", argv[0]);
    return 1;
  }

  snsrNew(&s); // (1)!
  snsrLoad(s, snsrStreamFromFileName(argv[1], "r")); // (2)!
  snsrSetStream(s, SNSR_SOURCE_AUDIO_PCM,
                snsrStreamFromAudioDevice(SNSR_ST_AF_DEFAULT)); // (3)!
  snsrSetHandler(s, SNSR_RESULT_EVENT,
                 snsrCallback(resultEvent, NULL, NULL)); // (4)!
  r = snsrRun(s); // (5)!
  if (r != SNSR_RC_STOP)
    fprintf(stderr, "ERROR: %s\n", snsrErrorDetail(s)); // (6)!
  snsrRelease(s); // (7)!

  return 0;
}

1. new — allocate an empty Session handle.
2. load the .snsr model from disk (pass a phrase-spot .snsr file, as on the Quick start page).
3. setStream attaches live PCM from the default capture device (fromAudioDevice).
4. setHandler registers resultEvent on the ^result event (callback).
5. run blocks until the handler returns STOP or an error RC.
6. On any code other than STOP, print errorDetail to stderr (same pattern as live-spot.c). The handler propagates RC errors from getString.
7. release frees the session and attached streams.

Create FirstSpot.java with:

import com.sensory.speech.snsr.Snsr;
import com.sensory.speech.snsr.SnsrRC;
import com.sensory.speech.snsr.SnsrSession;
import com.sensory.speech.snsr.SnsrStream;

public class FirstSpot {
  public static void main(String[] argv) throws Exception {
    if (argv.length != 1) {
      System.err.println("usage: FirstSpot spotter-model");
      System.exit(1);
    }

    SnsrSession s = new SnsrSession(); // (1)!
    s.load(argv[0]) // (2)!
        .setStream(Snsr.SOURCE_AUDIO_PCM, SnsrStream.fromAudioDevice()) // (3)!
        .setHandler(Snsr.RESULT_EVENT, (ses, key) -> { // (4)!
          System.out.println("Spotted \"" + ses.getString(Snsr.RES_TEXT) + "\".");
          return SnsrRC.STOP;
        });
    s.run(); // (5)!
    s.release(); // (6)!
  }
}

1. new SnsrSession() — empty Session (new).
2. load the .snsr model from the path in argv[0].
3. setStream with fromAudioDevice on the method chain.
4. setHandler on ^result; return STOP to end run.
5. run — pull-mode loop until the handler stops.
6. release the session.

Look up signatures under the Java tabs on Inference and I/O. The Java binding throws on failure instead of latched RC codes (see API overview § Language bindings).

Create first_spot.py with:

import sys

import snsr


def on_result(s: snsr.Session, _key: bytes) -> snsr.RC:
    phrase = s.get_string(snsr.RES_TEXT)
    print(f'Spotted "{phrase}".')
    return snsr.RC.STOP


def main() -> int:
    if len(sys.argv) != 2:
        print(f"usage: {sys.argv[0]} spotter-model", file=sys.stderr)
        return 1

    try:
        with snsr.Session() as s:
            s.load(sys.argv[1])  # (1)!
            s.set_stream(
                snsr.SOURCE_AUDIO_PCM,
                snsr.Stream.from_audio_device(),
            )  # (2)!
            s.set_handler(snsr.RESULT_EVENT, on_result)  # (3)!
            s.run()  # (4)!
    except snsr.Error as e:
        print(f"ERROR: {e.message}", file=sys.stderr)  # (5)!
        return 1
    return 0


if __name__ == "__main__":
    raise SystemExit(main())

1. load the .snsr model from the path on the command line.
2. set_stream attaches live PCM from the default capture device (fromAudioDevice, Stream.from_audio_device() in Python).
3. setHandler (set_handler in Python) registers on_result on the ^result event; return STOP to end run.
4. run — pull-mode loop until the handler stops.
5. On failure the binding raises snsr.Error with detail in Error.message (no latched RC codes on the session). A handler returning STOP is normal completion, not an error.

Look up signatures under the Python tabs on Inference and I/O. The shipped sample live_audio.py at ~/Sensory/TrulyNaturalSDK/7.8.0-pre.2/sample/python/src/live_audio.py adds a timed capture loop and more diagnostics.

Uses the Java Session API — see Java tabs on Inference for method details. The excerpt is the core wake-word-only flow in snsr-debug; the shipping app also uses a worker thread, UI, and optional debug logging. Both Java and Kotlin call sites use the same classes from the AAR; see API overview § Kotlin on Android for Kotlin interop notes.

SnsrStream audio = SnsrStream.fromAudioDevice();
SnsrSession session = new SnsrSession();
session.load(assetToString(BuildConfig.TRIGGER_MODEL))
    .setStream(Snsr.SOURCE_AUDIO_PCM, audio)
    .setHandler(Snsr.RESULT_EVENT, this);
session.run();

import com.sensory.speech.snsr.Snsr
import com.sensory.speech.snsr.SnsrRC
import com.sensory.speech.snsr.SnsrSession
import com.sensory.speech.snsr.SnsrStream

val audio = SnsrStream.fromAudioDevice()
val session = SnsrSession()
session.load(assetToString(BuildConfig.TRIGGER_MODEL))
    .setStream(Snsr.SOURCE_AUDIO_PCM, audio)
    .setHandler(Snsr.RESULT_EVENT) { ses, _ ->
        println("Spotted \"${ses.getString(Snsr.RES_TEXT)}\".")
        SnsrRC.STOP
    }
session.run()
session.release()

When you integrate into your own app, add RECORD_AUDIO to AndroidManifest.xml, use SnsrStream.fromAudioDevice(int device, int sampleRate) if you need a specific MediaRecorder.AudioSource, and follow Integrate with your build § Android.

Calls the C API from Swift — look up snsrLoad, snsrSetStream, and related functions under the C tabs on Inference and I/O. There is no Swift Session wrapper; PhraseSpot uses a bridging header and runs run on a background queue.

// Excerpt — see PhraseSpot.swift for load(), UI, and AVAudioSession setup.
snsrLoad(session, snsrStreamFromFileName(modelPath(modelName), "r"))
snsrSetStream(session, SNSR_SOURCE_AUDIO_PCM, snsrStreamFromDefaultAudioDevice())
snsrSetHandler(session, SNSR_RESULT_EVENT, resultCallback)
// snsrRun(session) — invoked on a background thread in the sample app.

Create a new directory anywhere (not under the SDK sample tree). The steps below assume ~/first-spot/.

Create a new directory anywhere (not under the SDK sample tree). The steps below assume ~/first-spot-java/.

export SNSR_ROOT=$HOME/Sensory/TrulyNaturalSDK/7.8.0-pre.2
SNSR_JAR=$(find "$SNSR_ROOT/m2repository" -name 'tnl-*.jar' \
  ! -name '*-sources.jar' -print -quit)
javac -cp "$SNSR_JAR" FirstSpot.java
# macOS example:
java -Djava.library.path="$SNSR_ROOT/lib/macos" \
  -cp ".:$SNSR_JAR" FirstSpot \
  "$SNSR_ROOT/model/spot-voicegenie-enUS-6.5.1-m.snsr"

Create a new directory anywhere (not under the SDK sample tree). The steps below assume ~/first-spot-python/.

Try the sample (no code changes)

Integrate in your own app

Use the Program excerpt as a guide, then follow Integrate with your build § Android and the Android examples. A from-scratch Android walk-through is not duplicated here (manifest, AAR, assets, and UI threading are app-specific).

Try the sample (no code changes)

Integrate in your own app

Use the Program excerpt and C API reference tabs, then follow Integrate with your build § iOS and iOS examples. Creating a new Xcode target from scratch is integration work, not covered step-by-step on this page.