Voice AI today understands what you say: the words, the language, the text. But it's deaf to how you actually sound — pitch, timbre, emotion, vocal quality, rhythm, melody. Everything that makes a voice a voice, not just a transcript.

VoxaTrace is an on-device SDK that makes any application acoustically intelligent.

Eight years of R&D. Five million users in production. All running natively on Android and iOS, without a single server call.

┌──────────────┬──────────────┬──────────────┬──────────────┬────────────┐
│    Sonix     │     Tona     │   Tessera    │    Accura    │  Calibra   │
│  Audio I/O   │    Pitch     │ Voice metrics│ Intonation   │  Singing   │
│              │              │              │ scoring      │  eval      │
├──────────────┼──────────────┼──────────────┼──────────────┼────────────┤
│ • Player     │ • Detection  │ • Breath     │ • EQ / JI    │ • LiveEval │
│ • Recorder   │ • Processing │ • Agility    │   per-note   │ • MelodyEv │
│ • Mixer      │ • Analysis   │ • Range      │   deviation  │ • NoteEval │
│ • Encoder    │   (histogram │ • Speaking   │ • 0–100      │ • VAD      │
│ • Decoder    │   transcr.)  │   pitch      │   scoring    │ • Effects  │
│ • Metronome  │              │              │              │            │
│ • MIDI synth │              │              │              │            │
└──────────────┴──────────────┴──────────────┴──────────────┴────────────┘

           Common: MusicTheory (Hz/MIDI/cents conversions, shruti alignment)

dependencies {
    implementation("com.musicmuni:voxatrace:2.0.0")
}

dependencies: [
    .package(url: "https://github.com/musicmuni/voxatrace", from: "2.0.0")
]

pod 'VoxaTrace', :podspec => 'https://raw.githubusercontent.com/musicmuni/voxatrace/main/VoxaTrace.podspec'

VT.initializeForServer("sk_live_…")  // see docs for proxy / attestation flows on mobile
val detector = PitchDetection.createDetector()
val point = detector.detect(audioSamples, sampleRate = 16000)
println("${point.pitch} Hz @ ${(point.confidence * 100).toInt()}% confidence")
detector.close()

let detector = PitchDetection.createDetector()
let point = detector.detect(samples: audioSamples, sampleRate: 16000)
print("\(point.pitch) Hz @ \(Int(point.confidence * 100))% confidence")
detector.close()

Output:

440.0 Hz @ 92% confidence

voxatrace.ai

Commercial. See LICENSE.

support@musicmuni.com