Crate denoize 

denoize — pure-Rust audio denoiser built for the world’s highest fidelity.

Goal: transparent, artifact-free restoration that preserves timbre, transients, dynamics, and “air” better than any classical offline tool.

Implemented technologies

Classical DSP (always available)

• STFT/ISTFT + Perfect Reconstruction OLA（高オーバーラップ対応）
• IMCRA/MCRA ノイズ推定 + Spectral Flatness プロファイル + Anchoring
• Ephraim-Malah Decision-Directed SNR
• 8種類のゲイン推定器（OMLSA, LogMMSE, MMSE-STSA, Wiener, SpecSub + 非線形/幾何学的）
• Attack/Release + Cepstral Smoothing + Transient Protection
• 高度窓関数: Kaiser / Flat-top / DPSS
• マルチバンドスペクトルサブトラクション
• 知覚重み付け（Bark帯域）+ 音楽ノイズ抑制ポストフィルタ

Input / output codecs (built-in, no ffmpeg)

• Decode: WAV / MP3 (symphonia, including Xing/LAME gapless timing, with a bounded raw-stream compatibility fallback) / M4A (Pure-Rust AAC-LC and ALAC with v0/v1 unity-rate edit-list presentation timing)
• Encode: WAV / MP3 (shine-rs) / M4A (oxideav-aac Pure-Rust AAC-LC)
• Decoded to f64 PCM at native sample rate (no extra quantisation)

Optional AI backends (feature-gated)

• rnnoise feature: RNNoise via nnnoiseless (pure-Rust)
• deepfilter feature: DeepFilterNet v3 via tract ONNX
• onnx feature: user-supplied waveform ONNX models via tract (including a reusable, contract-checked loaded-model API)
• aec feature: typed far-end-reference partitioned frequency-domain AEC
• mpsenet feature: MP-SENet compressed-magnitude/phase ONNX adapter
• bsrnn feature: ESPnet BSRNN spectral ONNX adapter
• mossformer2 feature: ClearerVoice MossFormer2 48 kHz ONNX adapter
• sgmse feature: SGMSE+ iterative diffusion ONNX adapter

Build with all backends: cargo build --release --features full

Re-exports

pub use acoustic_echo::estimate_aec_memory_bytes;

pub use acoustic_echo::sign_aec_promotion_evidence;

pub use acoustic_echo::AecBlockDiagnostics;

pub use acoustic_echo::AecClockMapping;

pub use acoustic_echo::AecConfig;

pub use acoustic_echo::AecDelayEstimate;

pub use acoustic_echo::AecEvidenceMetric;

pub use acoustic_echo::AecEvidenceMetricOperator;

pub use acoustic_echo::AecEvidenceStratum;

pub use acoustic_echo::AecEvidenceStratumKind;

pub use acoustic_echo::AecPromotionEvidencePayload;

pub use acoustic_echo::AecRealtimeAdapter;

pub use acoustic_echo::AecRealtimeDiagnostics;

pub use acoustic_echo::AecRenderReport;

pub use acoustic_echo::AecRenderResult;

pub use acoustic_echo::AecResetCounts;

pub use acoustic_echo::AecResetReason;

pub use acoustic_echo::AecSession;

pub use acoustic_echo::AecStream;

pub use acoustic_echo::AecTalkState;

pub use acoustic_echo::SignedAecPromotionEvidence;

pub use acoustic_echo::AEC_PROMOTION_EVIDENCE_SCHEMA;

pub use acoustic_echo::AEC_REPORT_SCHEMA;

pub use acoustic_echo::AEC_SCHEMA_VERSION;

pub use atomic_output::AtomicOutput;

pub use atomic_output::CommitMode;

pub use audio::ensure_memory_limit;

pub use audio::estimate_audio_memory_bytes;

pub use audio::estimate_audio_working_set_bytes;

pub use audio::estimate_file_memory_bytes;

pub use audio::estimate_session_memory_bytes;

pub use audio::estimate_stream_memory_bytes;

pub use audio::estimate_stream_memory_bytes_checked;

pub use audio::inspect_wav_session;

pub use audio::read_audio;

pub use audio::read_audio_from_session;

pub use audio::read_audio_from_session_with_limits;

pub use audio::read_audio_with_limits;

pub use audio::read_audio_with_metadata_limits;

pub use audio::read_wav;

pub use audio::read_wav_bytes;

pub use audio::read_wav_bytes_with_limits;

pub use audio::read_wav_from_session;

pub use audio::read_wav_from_session_with_limits;

pub use audio::read_wav_with_limits;

pub use audio::sanitize_sample;

pub use audio::write_audio;

pub use audio::write_wav;

pub use audio::write_wav_bytes;

pub use audio::write_wav_channel_mask;

pub use audio::Audio;

pub use audio::WavStreamInfo;

pub use audio::WavStreamReader;

pub use audio::WavStreamWriter;

pub use backend::gtcrn::GtcrnModel;

pub use backend::gtcrn::GtcrnStream;

pub use backend::onnx::OnnxWaveformContract;

pub use backend::onnx::OnnxWaveformLayout;

pub use backend::onnx::OnnxWaveformModel;

pub use backend::decode_mid_side;

pub use backend::encode_mid_side;

pub use backend::Backend;

pub use backend::BackendOptions;

pub use backend::BackendSession;

pub use backend::ChannelMode;

pub use backend::OnnxModelConfig;

pub use backend::SgmseProfile;

pub use backend::StreamingBackendSession;

pub use benchmark::ArtifactReport;

pub use benchmark::BenchmarkReport;

pub use benchmark::ComparisonReport;

pub use causal_target_sound::estimate_causal_target_sound_memory_bytes;

pub use causal_target_sound::sign_causal_target_sound_promotion_evidence;

pub use causal_target_sound::write_causal_target_sound_conservative_fallback;

pub use causal_target_sound::CausalTargetSoundBlock;

pub use causal_target_sound::CausalTargetSoundBlockDecision;

pub use causal_target_sound::CausalTargetSoundConfig;

pub use causal_target_sound::CausalTargetSoundDecisionCounts;

pub use causal_target_sound::CausalTargetSoundDeviceLatencyMeasurement;

pub use causal_target_sound::CausalTargetSoundEvidenceIdentity;

pub use causal_target_sound::CausalTargetSoundMetricEvidence;

pub use causal_target_sound::CausalTargetSoundModelIdentity;

pub use causal_target_sound::CausalTargetSoundPromotionEvidencePayload;

pub use causal_target_sound::CausalTargetSoundQueryIdentity;

pub use causal_target_sound::CausalTargetSoundRealtimeAudit;

pub use causal_target_sound::CausalTargetSoundRealtimeMetrics;

pub use causal_target_sound::CausalTargetSoundRealtimeReceiveError;

pub use causal_target_sound::CausalTargetSoundRealtimeResult;

pub use causal_target_sound::CausalTargetSoundRealtimeScheduler;

pub use causal_target_sound::CausalTargetSoundRealtimeSubmitError;

pub use causal_target_sound::CausalTargetSoundRealtimeToken;

pub use causal_target_sound::CausalTargetSoundRenderReport;

pub use causal_target_sound::CausalTargetSoundRenderResult;

pub use causal_target_sound::CausalTargetSoundSession;

pub use causal_target_sound::CausalTargetSoundSnapshot;

pub use causal_target_sound::CausalTargetSoundSnapshotState;

pub use causal_target_sound::CausalTargetSoundStratumEvidence;

pub use causal_target_sound::CausalTargetSoundStream;

pub use causal_target_sound::CausalTargetSoundTransitionAudit;

pub use causal_target_sound::SignedCausalTargetSoundPromotionEvidence;

pub use causal_target_sound::CAUSAL_TARGET_SOUND_EVIDENCE_SCHEMA;

pub use causal_target_sound::CAUSAL_TARGET_SOUND_REPORT_SCHEMA;

pub use causal_target_sound::CAUSAL_TARGET_SOUND_SCHEMA_VERSION;

pub use causal_target_sound::CAUSAL_TARGET_SOUND_SNAPSHOT_SCHEMA;

pub use causal_target_speaker::estimate_causal_target_speaker_memory_bytes;

pub use causal_target_speaker::sign_causal_target_speaker_promotion_evidence;

pub use causal_target_speaker::CausalTargetSpeakerBlock;

pub use causal_target_speaker::CausalTargetSpeakerBlockDecision;

pub use causal_target_speaker::CausalTargetSpeakerConfig;

pub use causal_target_speaker::CausalTargetSpeakerDecisionCounts;

pub use causal_target_speaker::CausalTargetSpeakerEnrollmentSummary;

pub use causal_target_speaker::CausalTargetSpeakerEvidenceIdentity;

pub use causal_target_speaker::CausalTargetSpeakerMetricEvidence;

pub use causal_target_speaker::CausalTargetSpeakerModelIdentity;

pub use causal_target_speaker::CausalTargetSpeakerPromotionEvidencePayload;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeAudit;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeMetrics;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeReceiveError;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeResult;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeScheduler;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeSubmitError;

pub use causal_target_speaker::CausalTargetSpeakerRealtimeToken;

pub use causal_target_speaker::CausalTargetSpeakerRenderReport;

pub use causal_target_speaker::CausalTargetSpeakerRenderResult;

pub use causal_target_speaker::CausalTargetSpeakerSession;

pub use causal_target_speaker::CausalTargetSpeakerStratumEvidence;

pub use causal_target_speaker::CausalTargetSpeakerStream;

pub use causal_target_speaker::CausalTargetSpeakerTransitionAudit;

pub use causal_target_speaker::SignedCausalTargetSpeakerPromotionEvidence;

pub use causal_target_speaker::CAUSAL_TARGET_SPEAKER_PROMOTION_EVIDENCE_SCHEMA;

pub use causal_target_speaker::CAUSAL_TARGET_SPEAKER_REPORT_SCHEMA;

pub use causal_target_speaker::CAUSAL_TARGET_SPEAKER_SCHEMA_VERSION;

pub use channel_layout::ChannelLayout;

pub use channel_layout::ChannelMask;

pub use channel_layout::ChannelPosition;

pub use channel_layout::PanInfo;

pub use config::ConfigError;

pub use config::ResourcePlan;

pub use daw::read_daw_preset;

pub use daw::read_daw_session;

pub use daw::write_daw_preset;

pub use daw::write_daw_session;

pub use daw::DawParameters;

pub use daw::DawPortConfiguration;

pub use daw::DawPreset;

pub use daw::DawRealtimeParameters;

pub use daw::DawRealtimeProcessor;

pub use daw::DawSessionState;

pub use daw::DAW_FIXED_LATENCY_MILLIS;

pub use daw::DAW_LATENCY_POLICY;

pub use daw::DAW_MAX_SAMPLE_RATE;

pub use daw::DAW_PLUGIN_ID;

pub use daw::DAW_PRESET_SCHEMA;

pub use daw::DAW_PRESET_SCHEMA_VERSION;

pub use daw::DAW_SESSION_SCHEMA;

pub use daw::DAW_SESSION_SCHEMA_VERSION;

pub use decode::decode_file;

pub use decode::decode_file_from_session_with_limits;

pub use decode::decode_file_with_limits;

pub use decode::decode_file_with_metadata_limits;

pub use decode::inspect_audio_stream_session;

pub use decode::probe_file;

pub use decode::probe_file_from_session_with_limits;

pub use decode::probe_file_with_limits;

pub use decode::probe_file_with_metadata_limits;

pub use decode::AudioCodec;

pub use decode::AudioFormat;

pub use decode::AudioProbe;

pub use decode::AudioStreamInfo;

pub use decode::AudioStreamReader;

pub use decode::DecodeLimits;

pub use decode::DecodedPcm;

pub use denoiser::Denoiser;

pub use denoiser::DenoiserConfig;

pub use denoiser::Preset;

pub use denoiser::ProcessingMode;

pub use denoiser::StreamingDenoiser;

pub use diagnostics::assess_file_with_options;

pub use diagnostics::compare_files_with_options;

pub use diagnostics::diagnose_audio;

pub use diagnostics::diagnose_file;

pub use diagnostics::diagnose_file_with_options;

pub use diagnostics::AssessmentComparison;

pub use diagnostics::AssessmentReport;

pub use diagnostics::DiagnosticFinding;

pub use diagnostics::DiagnosticInput;

pub use diagnostics::DiagnosticMetrics;

pub use diagnostics::DiagnosticOptions;

pub use diagnostics::DiagnosticReport;

pub use diagnostics::NoReferenceQuality;

pub use diagnostics::ASSESSMENT_SCHEMA;

pub use diagnostics::ASSESSMENT_SCHEMA_VERSION;

pub use diagnostics::DIAGNOSTIC_SCHEMA;

pub use diagnostics::DIAGNOSTIC_SCHEMA_VERSION;

pub use encode::estimate_spooled_stream_output_bytes;

pub use encode::estimate_stream_encode_additional_bytes;

pub use encode::estimate_stream_encode_output_bytes;

pub use encode::estimate_stream_encode_temporary_bytes;

pub use encode::estimate_stream_output_verification_bytes;

pub use encode::verify_stream_output_file;

pub use encode::AacEncoder;

pub use encode::AudioStreamWriter;

pub use encode::DownmixMode;

pub use encode::EncodeOptions;

pub use encode::OutputFormat;

pub use encode::SpooledAudioStreamWriter;

pub use encode::StreamEncodeLimits;

pub use encode::StreamEncodeSpec;

pub use encode::StreamOutputVerification;

pub use encode::StreamPcmSpool;

pub use evaluation::compare_evaluation_results;

pub use evaluation::run_evaluation;

pub use evaluation::validate_evaluation_corpus;

pub use evaluation::verify_evaluation_result;

pub use evaluation::write_signed_evaluation_result;

pub use evaluation::EvaluationArtifact;

pub use evaluation::EvaluationCase;

pub use evaluation::EvaluationCaseResult;

pub use evaluation::EvaluationComparisonReport;

pub use evaluation::EvaluationCorpusValidation;

pub use evaluation::EvaluationEnvironment;

pub use evaluation::EvaluationLicense;

pub use evaluation::EvaluationManifest;

pub use evaluation::EvaluationPolicy;

pub use evaluation::EvaluationRecipe;

pub use evaluation::EvaluationResultPayload;

pub use evaluation::EvaluationSource;

pub use evaluation::EvaluationThreshold;

pub use evaluation::EvaluationVerificationReport;

pub use evaluation::ListeningEvidence;

pub use evaluation::ListeningPolicy;

pub use evaluation::ListeningProtocol;

pub use evaluation::ListeningTestResult;

pub use evaluation::ObjectiveEvaluationMetrics;

pub use evaluation::OutputQualityMetrics;

pub use evaluation::PerformanceMetrics;

pub use evaluation::RegressionDirection;

pub use evaluation::RegressionOutcome;

pub use evaluation::RegressionTolerance;

pub use evaluation::SignalPreparation;

pub use evaluation::SignedEvaluationResult;

pub use evaluation::ThresholdAggregation;

pub use evaluation::ThresholdOperator;

pub use evaluation::ThresholdOutcome;

pub use evaluation::EVALUATION_COMPARISON_SCHEMA;

pub use evaluation::EVALUATION_CORPUS_SCHEMA;

pub use evaluation::EVALUATION_CORPUS_VERIFICATION_SCHEMA;

pub use evaluation::EVALUATION_RESULT_SCHEMA;

pub use evaluation::EVALUATION_SCHEMA_VERSION;

pub use evaluation::EVALUATION_VERIFICATION_SCHEMA;

pub use evaluation::LISTENING_RESULT_SCHEMA;

pub use execution::execution_item_id;

pub use execution::export_receipt_public_key;

pub use execution::generate_receipt_keypair;

pub use execution::portable_file_locator;

pub use execution::portable_locator;

pub use execution::write_execution_plan;

pub use execution::write_new_receipt_keypair;

pub use execution::write_receipt_trust_policy;

pub use execution::write_signed_receipt;

pub use execution::ExecutionKind;

pub use execution::ExecutionPlan;

pub use execution::ExecutionPlanItem;

pub use execution::ExecutionReceiptPayload;

pub use execution::PlannedArtifact;

pub use execution::PlannedOutput;

pub use execution::PlannedResources;

pub use execution::ReceiptItem;

pub use execution::ReceiptOutput;

pub use execution::ReceiptPublicKey;

pub use execution::ReceiptSecretKey;

pub use execution::ReceiptSignature;

pub use execution::ReceiptTrustPolicy;

pub use execution::ReceiptVerificationReport;

pub use execution::SignedExecutionReceipt;

pub use execution::VerifiedReceiptItem;

pub use execution::EXECUTION_PLAN_SCHEMA;

pub use execution::EXECUTION_RECEIPT_SCHEMA;

pub use execution::EXECUTION_SCHEMA_VERSION;

pub use execution::RECEIPT_PUBLIC_KEY_SCHEMA;

pub use execution::RECEIPT_SECRET_KEY_SCHEMA;

pub use execution::RECEIPT_TRUST_POLICY_SCHEMA;

pub use execution::RECEIPT_VERIFICATION_SCHEMA;

pub use execution::STREAM_EXECUTION_PLAN_SCHEMA;

pub use execution::STREAM_EXECUTION_RECEIPT_SCHEMA;

pub use execution::STREAM_EXECUTION_SCHEMA_VERSION;

pub use execution::STREAM_RECEIPT_VERIFICATION_SCHEMA;

pub use gain::Algorithm;

pub use gain::SpecSubLaw;

pub use hardware::backend_supports_acceleration;

pub use hardware::hardware_capabilities;

pub use hardware::select_accelerator;

pub use hardware::select_accelerator_for_options;

pub use hardware::AcceleratorFallback;

pub use hardware::AcceleratorPreference;

pub use hardware::AcceleratorRuntime;

pub use hardware::AcceleratorSelection;

pub use hardware::BackendCapability;

pub use hardware::HardwareCapabilities;

pub use hardware::RuntimeCapability;

pub use hardware::HARDWARE_SCHEMA;

pub use hardware::HARDWARE_SCHEMA_VERSION;

pub use input::AudioInputSession;

pub use input::StreamSpoolLimits;

pub use meeting_speaker::MeetingSpeakerSession;

pub use meeting_speaker::estimate_meeting_speaker_memory_bytes;

pub use meeting_speaker::sign_meeting_speaker_promotion_evidence;

pub use meeting_speaker::MeetingActivityState;

pub use meeting_speaker::MeetingRegion;

pub use meeting_speaker::MeetingSpeakerConfig;

pub use meeting_speaker::MeetingSpeakerEvidenceIdentity;

pub use meeting_speaker::MeetingSpeakerEvidenceStratum;

pub use meeting_speaker::MeetingSpeakerModelIdentity;

pub use meeting_speaker::MeetingSpeakerPromotionEvidencePayload;

pub use meeting_speaker::MeetingSpeakerReport;

pub use meeting_speaker::MeetingSpeakerResult;

pub use meeting_speaker::MeetingSpeakerSegment;

pub use meeting_speaker::MeetingSpeakerTrackSummary;

pub use meeting_speaker::MeetingTrackLabel;

pub use meeting_speaker::MeetingTrackLabelsDocument;

pub use meeting_speaker::SignedMeetingSpeakerPromotionEvidence;

pub use meeting_speaker::MAX_MEETING_SPEAKER_TRACKS;

pub use meeting_speaker::MEETING_SPEAKER_EVIDENCE_SCHEMA;

pub use meeting_speaker::MEETING_SPEAKER_REPORT_SCHEMA;

pub use meeting_speaker::MEETING_SPEAKER_SCHEMA_VERSION;

pub use meeting_speaker::MEETING_TRACK_LABELS_SCHEMA;

pub use microphone_array::estimate_microphone_array_memory_bytes;

pub use microphone_array::sign_microphone_array_promotion_evidence;

pub use microphone_array::ArrayCoordinateUnit;

pub use microphone_array::ArrayHandedness;

pub use microphone_array::ArrayInputSemantics;

pub use microphone_array::MicrophoneArrayConfig;

pub use microphone_array::MicrophoneArrayEvidenceStratum;

pub use microphone_array::MicrophoneArrayGeometry;

pub use microphone_array::MicrophoneArrayPromotionEvidencePayload;

pub use microphone_array::MicrophoneArrayReport;

pub use microphone_array::MicrophoneArrayResult;

pub use microphone_array::MicrophoneArraySession;

pub use microphone_array::MicrophonePosition;

pub use microphone_array::SignedMicrophoneArrayPromotionEvidence;

pub use microphone_array::MICROPHONE_ARRAY_EVIDENCE_SCHEMA;

pub use microphone_array::MICROPHONE_ARRAY_REPORT_SCHEMA;

pub use microphone_array::MICROPHONE_ARRAY_SCHEMA_VERSION;

pub use model_package::build_runtime_model_package;

pub use model_package::build_runtime_model_package_v2;

pub use model_package::inspect_runtime_model_package;

pub use model_package::RuntimeModelAxisContractV2;

pub use model_package::RuntimeModelChannelContractV2;

pub use model_package::RuntimeModelChannelRoleContractV2;

pub use model_package::RuntimeModelComponentContractV2;

pub use model_package::RuntimeModelFileContract;

pub use model_package::RuntimeModelFrontendContract;

pub use model_package::RuntimeModelFrontendContractV2;

pub use model_package::RuntimeModelGeometryContractV2;

pub use model_package::RuntimeModelLatencyContractV2;

pub use model_package::RuntimeModelLicenseContract;

pub use model_package::RuntimeModelLicenseContractV2;

pub use model_package::RuntimeModelMicrophonePositionV2;

pub use model_package::RuntimeModelNumericalCaseV1;

pub use model_package::RuntimeModelNumericalTensorV1;

pub use model_package::RuntimeModelNumericalToleranceV1;

pub use model_package::RuntimeModelNumericalVectorsV1;

pub use model_package::RuntimeModelPackage;

pub use model_package::RuntimeModelPackageInfo;

pub use model_package::RuntimeModelPackageManifest;

pub use model_package::RuntimeModelPackageManifestV2;

pub use model_package::RuntimeModelPackageReader;

pub use model_package::RuntimeModelPackageV2Info;

pub use model_package::RuntimeModelPrecisionProfileContractV2;

pub use model_package::RuntimeModelProvenanceContractV2;

pub use model_package::RuntimeModelResourceContract;

pub use model_package::RuntimeModelRuntimeContract;

pub use model_package::RuntimeModelRuntimeContractV2;

pub use model_package::RuntimeModelStatePairContractV2;

pub use model_package::RuntimeModelTensorContract;

pub use model_package::RuntimeModelTensorContractV2;

pub use model_package::RuntimeModelTensorSetContractV2;

pub use model_package::RuntimeModelTrainingDatasetContractV2;

pub use model_package::RUNTIME_MODEL_PACKAGE_SCHEMA;

pub use model_package::RUNTIME_MODEL_PACKAGE_SCHEMA_V2;

pub use model_package::RUNTIME_MODEL_PACKAGE_VERSION;

pub use model_package::RUNTIME_MODEL_PACKAGE_VERSION_V2;

pub use music_restoration::MusicRestorationSession;

pub use music_restoration::estimate_music_restoration_memory_bytes;

pub use music_restoration::sign_music_restoration_promotion_evidence;

pub use music_restoration::MusicRestorationConfig;

pub use music_restoration::MusicRestorationDecision;

pub use music_restoration::MusicRestorationEvidenceIdentity;

pub use music_restoration::MusicRestorationEvidenceStratum;

pub use music_restoration::MusicRestorationModelIdentity;

pub use music_restoration::MusicRestorationPromotionEvidencePayload;

pub use music_restoration::MusicRestorationRegion;

pub use music_restoration::MusicRestorationReport;

pub use music_restoration::MusicRestorationResult;

pub use music_restoration::MusicRestorationTask;

pub use music_restoration::MusicRestorationTrainingDatasetIdentity;

pub use music_restoration::SignedMusicRestorationPromotionEvidence;

pub use music_restoration::MUSIC_RESTORATION_EVIDENCE_SCHEMA;

pub use music_restoration::MUSIC_RESTORATION_REPORT_SCHEMA;

pub use music_restoration::MUSIC_RESTORATION_SCHEMA_VERSION;

pub use neural_daw::neural_daw_chunk_frames;

pub use neural_daw::neural_daw_latency_frames;

pub use neural_daw::neural_daw_latency_millis;

pub use neural_daw::read_neural_daw_session;

pub use neural_daw::write_neural_daw_session;

pub use neural_daw::NeuralDawOverloadFallback;

pub use neural_daw::NeuralDawParameters;

pub use neural_daw::NeuralDawPortConfiguration;

pub use neural_daw::NeuralDawSessionState;

pub use neural_daw::NEURAL_DAW_CHUNK_MILLIS;

pub use neural_daw::NEURAL_DAW_LATENCY_CHUNKS;

pub use neural_daw::NEURAL_DAW_LATENCY_POLICY;

pub use neural_daw::NEURAL_DAW_MAX_SAMPLE_RATE;

pub use neural_daw::NEURAL_DAW_MODEL_ID;

pub use neural_daw::NEURAL_DAW_MODEL_SHA256;

pub use neural_daw::NEURAL_DAW_PLUGIN_ID;

pub use neural_daw::NEURAL_DAW_SESSION_SCHEMA;

pub use neural_daw::NEURAL_DAW_SESSION_SCHEMA_VERSION;

pub use project::assemble_project_timeline;

pub use project::build_project_bundle;

pub use project::import_project_bundle;

pub use project::inspect_project_bundle;

pub use project::inspect_project_source;

pub use project::project_artifact_reference;

pub use project::relocate_project_source;

pub use project::run_project_batch;

pub use project::validate_project_files;

pub use project::write_project_execution_plan;

pub use project::write_project_manifest;

pub use project::write_signed_project_execution_receipt;

pub use project::ProjectArtifactReference;

pub use project::ProjectBatchItemReport;

pub use project::ProjectBatchReport;

pub use project::ProjectBatchRequest;

pub use project::ProjectBundleBinding;

pub use project::ProjectBundleBindingKind;

pub use project::ProjectBundleBuildOptions;

pub use project::ProjectBundleFileInfo;

pub use project::ProjectBundleImportReport;

pub use project::ProjectBundleInfo;

pub use project::ProjectExecutionPlan;

pub use project::ProjectExecutionReceiptPayload;

pub use project::ProjectManifest;

pub use project::ProjectModelReference;

pub use project::ProjectReceiptVerificationReport;

pub use project::ProjectRenderReport;

pub use project::ProjectSelection;

pub use project::ProjectSource;

pub use project::ProjectSourceInspection;

pub use project::ProjectTimeline;

pub use project::ProjectValidationReport;

pub use project::SignedProjectExecutionReceipt;

pub use project::PROJECT_BATCH_SCHEMA;

pub use project::PROJECT_BUNDLE_IMPORT_SCHEMA;

pub use project::PROJECT_BUNDLE_SCHEMA;

pub use project::PROJECT_EXECUTION_PLAN_SCHEMA;

pub use project::PROJECT_EXECUTION_RECEIPT_SCHEMA;

pub use project::PROJECT_MANIFEST_SCHEMA;

pub use project::PROJECT_MANIFEST_SCHEMA_VERSION;

pub use project::PROJECT_RECEIPT_VERIFICATION_SCHEMA;

pub use project::PROJECT_RENDER_SCHEMA;

pub use project::PROJECT_VALIDATION_SCHEMA;

pub use project::PROJECT_WATCH_CYCLE_SCHEMA;

pub use quality::QualityMetrics;

pub use recommendation::recommend_audio;

pub use recommendation::recommend_file;

pub use recommendation::recommend_file_with_options;

pub use recommendation::run_device_calibration;

pub use recommendation::CalibrationEvidence;

pub use recommendation::RecommendationCandidate;

pub use recommendation::RecommendationDecision;

pub use recommendation::RecommendationDevice;

pub use recommendation::RecommendationGoal;

pub use recommendation::RecommendationInput;

pub use recommendation::RecommendationMaterial;

pub use recommendation::RecommendationOptions;

pub use recommendation::RecommendationReason;

pub use recommendation::RecommendationReport;

pub use recommendation::RECOMMENDATION_SCHEMA;

pub use recommendation::RECOMMENDATION_SCHEMA_VERSION;

pub use region::PresentationRegion;

pub use region::PRESENTATION_REGION_SCHEMA;

pub use region::PRESENTATION_REGION_SCHEMA_VERSION;

pub use resource::estimate_backend_session_request;

pub use resource::estimate_backend_worker_gpu_memory_bytes;

pub use resource::estimate_backend_worker_memory_bytes;

pub use resource::estimate_gpu_session_bytes;

pub use resource::estimate_gpu_worker_bytes;

pub use resource::estimate_model_session_bytes;

pub use resource::estimate_temporary_bytes;

pub use resource::metadata_limits_after_retained_memory;

pub use resource::metadata_limits_for_available_memory;

pub use resource::ResourceGovernor;

pub use resource::ResourceLimits;

pub use resource::ResourcePermit;

pub use resource::ResourceRequest;

pub use resource::ResourceUsage;

pub use restoration::estimate_restoration_memory_bytes;

pub use restoration::restore_audio;

pub use restoration::DeclickConfig;

pub use restoration::DeclipConfig;

pub use restoration::DehumConfig;

pub use restoration::RestorationConfig;

pub use restoration::RestorationMask;

pub use restoration::RestorationMaskRun;

pub use restoration::RestorationMaskState;

pub use restoration::RestorationMode;

pub use restoration::RestorationOperation;

pub use restoration::RestorationOperationDetails;

pub use restoration::RestorationOperationReport;

pub use restoration::RestorationReport;

pub use restoration::RestorationResult;

pub use restoration::RestorationStatus;

pub use restoration::WindPlosiveConfig;

pub use restoration::WpeChannelMode;

pub use restoration::WpeConfig;

pub use restoration::MAX_RESTORATION_CHANNELS;

pub use restoration::MAX_RESTORATION_MASK_RUNS;

pub use restoration::MAX_RESTORATION_OPERATIONS;

pub use restoration::RESTORATION_MASK_SCHEMA;

pub use restoration::RESTORATION_REPORT_SCHEMA;

pub use restoration::RESTORATION_SCHEMA_VERSION;

pub use target_sound::TargetSoundSession;

pub use target_sound::estimate_target_sound_memory_bytes;

pub use target_sound::sign_target_sound_promotion_evidence;

pub use target_sound::SignedTargetSoundPromotionEvidence;

pub use target_sound::TargetSoundCatalogClass;

pub use target_sound::TargetSoundConfig;

pub use target_sound::TargetSoundDecision;

pub use target_sound::TargetSoundEvidenceIdentity;

pub use target_sound::TargetSoundEvidenceStratum;

pub use target_sound::TargetSoundMetricOperator;

pub use target_sound::TargetSoundMetricOutcome;

pub use target_sound::TargetSoundMode;

pub use target_sound::TargetSoundModelIdentity;

pub use target_sound::TargetSoundPresence;

pub use target_sound::TargetSoundPresenceAssessment;

pub use target_sound::TargetSoundPromotionEvidencePayload;

pub use target_sound::TargetSoundQuery;

pub use target_sound::TargetSoundQueryIdentity;

pub use target_sound::TargetSoundReport;

pub use target_sound::TargetSoundResult;

pub use target_sound::TargetSoundSafetyGate;

pub use target_sound::TargetSoundSafetyGateKind;

pub use target_sound::TargetSoundSafetyMeasurements;

pub use target_sound::TargetSoundStratumKind;

pub use target_sound::TargetSoundTrainingDatasetIdentity;

pub use target_sound::MAX_TARGET_SOUND_AUDIO_SECONDS;

pub use target_sound::MAX_TARGET_SOUND_CLASSES;

pub use target_sound::MAX_TARGET_SOUND_WINDOWS;

pub use target_sound::TARGET_SOUND_EVIDENCE_SCHEMA;

pub use target_sound::TARGET_SOUND_QUERY_SCHEMA;

pub use target_sound::TARGET_SOUND_REPORT_SCHEMA;

pub use target_sound::TARGET_SOUND_SCHEMA_VERSION;

pub use target_speaker::TargetSpeakerSession;

pub use target_speaker::estimate_target_speaker_memory_bytes;

pub use target_speaker::sign_target_speaker_promotion_evidence;

pub use target_speaker::SignedTargetSpeakerPromotionEvidence;

pub use target_speaker::TargetSpeakerDecision;

pub use target_speaker::TargetSpeakerEnrollmentSummary;

pub use target_speaker::TargetSpeakerEvidenceIdentity;

pub use target_speaker::TargetSpeakerExtractionConfig;

pub use target_speaker::TargetSpeakerExtractionReport;

pub use target_speaker::TargetSpeakerExtractionResult;

pub use target_speaker::TargetSpeakerMetricOperator;

pub use target_speaker::TargetSpeakerMetricOutcome;

pub use target_speaker::TargetSpeakerModelIdentity;

pub use target_speaker::TargetSpeakerPresence;

pub use target_speaker::TargetSpeakerPresenceAssessment;

pub use target_speaker::TargetSpeakerPromotionEvidencePayload;

pub use target_speaker::TargetSpeakerSafetyGate;

pub use target_speaker::TargetSpeakerSafetyGateKind;

pub use target_speaker::TargetSpeakerSafetyMeasurements;

pub use target_speaker::TargetSpeakerStratumEvidence;

pub use target_speaker::TargetSpeakerStratumKind;

pub use target_speaker::MAX_TARGET_SPEAKER_ENROLLMENT_MILLIS;

pub use target_speaker::MAX_TARGET_SPEAKER_EVIDENCE_METRICS;

pub use target_speaker::MAX_TARGET_SPEAKER_EVIDENCE_STRATA;

pub use target_speaker::MAX_TARGET_SPEAKER_MIXTURE_SECONDS;

pub use target_speaker::MIN_TARGET_SPEAKER_ENROLLMENT_MILLIS;

pub use target_speaker::TARGET_SPEAKER_PROMOTION_EVIDENCE_SCHEMA;

pub use target_speaker::TARGET_SPEAKER_REPORT_SCHEMA;

pub use target_speaker::TARGET_SPEAKER_SCHEMA_VERSION;

pub use universal_restoration::restore_universal_audio;

pub use universal_restoration::estimate_universal_restoration_memory_bytes;

pub use universal_restoration::sign_universal_promotion_evidence;

pub use universal_restoration::SignedUniversalPromotionEvidence;

pub use universal_restoration::UniversalDegradation;

pub use universal_restoration::UniversalDegradationEvidence;

pub use universal_restoration::UniversalMaskRun;

pub use universal_restoration::UniversalMaskState;

pub use universal_restoration::UniversalMetricOperator;

pub use universal_restoration::UniversalMetricOutcome;

pub use universal_restoration::UniversalModelFamily;

pub use universal_restoration::UniversalModelIdentity;

pub use universal_restoration::UniversalPromotionEvidencePayload;

pub use universal_restoration::UniversalRenderRole;

pub use universal_restoration::UniversalRestorationConfig;

pub use universal_restoration::UniversalRestorationDecision;

pub use universal_restoration::UniversalRestorationMask;

pub use universal_restoration::UniversalRestorationReport;

pub use universal_restoration::UniversalRestorationResult;

pub use universal_restoration::UniversalSafetyGate;

pub use universal_restoration::UniversalSafetyGateKind;

pub use universal_restoration::UniversalSafetyMeasurements;

pub use universal_restoration::UniversalStratumEvidence;

pub use universal_restoration::MAX_UNIVERSAL_EVIDENCE_METRICS;

pub use universal_restoration::MAX_UNIVERSAL_EVIDENCE_STRATA;

pub use universal_restoration::MAX_UNIVERSAL_MASK_RUNS;

pub use universal_restoration::UNIVERSAL_PROMOTION_EVIDENCE_SCHEMA;

pub use universal_restoration::UNIVERSAL_RESTORATION_MASK_SCHEMA;

pub use universal_restoration::UNIVERSAL_RESTORATION_REPORT_SCHEMA;

pub use universal_restoration::UNIVERSAL_RESTORATION_SCHEMA_VERSION;

pub use watch::WatchCycleReport;

pub use watch::WatchFolder;

pub use watch::WatchFolderConfig;

pub use watch::WatchFolderJob;

pub use watch::WatchProcessError;

pub use watch::WATCH_CYCLE_SCHEMA;

pub use watch::WATCH_QUARANTINE_SCHEMA;

pub use watch::WATCH_SCHEMA_VERSION;

pub use watch::WATCH_STATE_SCHEMA;

pub use window::WindowParams;

pub use window::WindowType;

Modules

acoustic_echo

Typed far-end-reference acoustic echo cancellation.

atomic_output

Atomic creation and replacement of filesystem outputs.

audio

Audio file I/O: WAV read/write (hound) + unified decode for MP3/M4A/WAV.

automation

Stable, read-only automation snapshots.

backend

Optional AI denoising backends (feature-gated).

benchmark

Objective quality and stereo-imaging reports.

bessel

Special functions needed by the Ephraim-Malah family of gain estimators: modified Bessel functions of the first kind, orders 0 and 1, and the exponential integral E1.

causal_target_sound

Fail-closed causal extraction of one sound from an authenticated finite catalog.

causal_target_speaker

Fail-closed causal target-speaker extraction.

channel_layout

Standard channel layouts used by the audio pipeline.

config

Shared validation and resource-planning primitives for external input.

daw

Real-time-safe DSP and portable state contracts for the DAW plug-in.

decode

denoize 自作デコード層 — lossless / lossy audio containers を高品質 PCM (f64) へ。

denoiser

The de-noizer: ties together STFT, IMCRA noise estimation, the decision-directed a-priori SNR estimator, the selected spectral gain estimator, attack/release + cepstral gain smoothing, transient protection, and optional pre-emphasis.

diagnostics

Bounded, network-free audio degradation diagnosis and no-reference quality assessment.

encode

Audio encode layer for bounded WAV, FLAC, Ogg Opus, MP3, M4A, and ADTS AAC output.

evaluation

Reproducible licensed-corpus evaluation and signed release evidence.

execution

Stable execution plans, signed receipts, and offline result verification.

fft

A self-contained, allocation-light, iterative radix-2 Cooley-Tukey FFT.

gain

Spectral gain estimators.

hardware

Compute capability discovery and explicit accelerator selection.

input

Stable, regular-file-backed audio input sessions.

ipc

Local authenticated IPC and durable job control.

loudness

EBU R128 / ITU-R BS.1770 loudness measurement and normalization.

meeting_speaker

Bounded continuous speech separation and anonymous meeting diarization.

metadata

Cross-container audio metadata preservation.

microphone_array

Explicit-geometry microphone-array enhancement.

model_package

Signed, self-describing runtime packages for custom waveform models.

models

Signed external-model catalog, verified local cache, and installation provenance.

music_restoration

Bounded candidate restoration for complete mono or stereo music programs.

neural_daw

Portable contracts shared by the off-callback neural DAW plug-in and its CLI/Desktop control surfaces.

noise

Noise-power-spectral-density estimation.

perceptual

Perceptual weighting for spectral gain control.

postfilter

Musical-noise suppression post-filter.

project

Portable, source-bound partial-file timelines.

project_v2

Durable, content-addressed non-destructive project graphs.

quality

Full-reference perceptual quality metrics.

recommendation

Network-free, explainable processing recommendations.

region

Stable, source-bound presentation regions.

resample

Band-limited, channel-synchronous sample-rate conversion.

resource

Process-wide admission control for bounded denoising work.

restoration

Deterministic, inspectable audio restoration.

sdk

Stable SDK capability and mobile lifecycle contracts.

service

Shared application service used by the CLI and graphical frontends.

stft

Short-time Fourier transform engine with perfect-reconstruction overlap-add (OLA) synthesis.

stream

Stateful block-processing API for realtime and pipe integrations.

target_sound

Fail-closed offline extraction of one sound from a finite semantic catalog.

target_speaker

Fail-closed offline target-speaker extraction and promotion evidence.

universal_restoration

Fail-closed orchestration and evidence contracts for universal speech restoration.

update

Authenticated, recoverable application-update transactions.

vad

Lightweight energy VAD and speech-region segmentation.

watch

Durable local watch-folder automation.

window

Window functions for short-time Fourier analysis/synthesis.

Functions

denoise_audio_with_backend_config

Process already-decoded audio in place. This is the path used by stdin and embedders that do not have filesystem-backed input.

denoise_audio_with_backend_session

Process decoded audio with a prepared backend graph.

denoise_file

Denoise a WAV file end-to-end, writing the result to output.

denoise_file_with_backend

Denoise with an explicit backend (classical / rnnoise / deepfilter).

denoise_file_with_backend_config

Denoise with explicit backend, encoder, and backend-specific model options.

denoise_file_with_backend_opts

Denoise with explicit backend and output encode options.

write_audio_transactional

Encode audio and optional metadata into a staged file, then publish it in one filesystem commit.

write_audio_transactional_as

Encode audio using a format selected during preflight, then publish it in one filesystem commit without re-inferring the codec from the path.