Skip to main content

Module audio_pipeline

Module audio_pipeline 

Source
Expand description

Client-facing auditory Ears MVP + later swarm helpers.

Structs§

AudioCapabilityDto
Honest, machine-readable status of one audio capability (for Listen UI honesty chips).
CrossModalDemoDto
EarsDemoDto
MixerTrackDto
One mixer track strip (UI ↔ process plan).

Functions§

analyze_mono_pcm
Run weighted AED on mono PCM (from mic pull or file).
audio_capabilities
Snapshot the audio capability registry as serializable DTOs.
audio_correct_instance
Appends a human-correct attestation quin for an audio instance.
audio_reject_instance
Appends a human-reject attestation quin for an audio instance.
capture_policy_demo
Capture policy demo: intent required before live ring accepts PCM.
cross_modal_demo
Cross-modal pipeline demo.
daw_fx_demo
DAW FX chain demo (EQ + comp + delay on mono).
daw_history_demo
DAW history demo.
ears_demo
EARS pipeline demo (self-marking synthetic input).
ears_from_wav
EARS pipeline over a WAV file.
ears_weighted_demo
Weighted EARS demo.
ensure_aed_weights
Seed and persist AED weights under storage_root/models/aed_seed.qaed
ensure_speech_weights
Ensures speech-weights.
gen_audio_demo
TTS consent + stem separation demo.
mixer_bounce
Bounce a mixer session (synthetic tones per track) through ProcessPlan FX chain.
mixer_default_session
Default 3-strip mixer session for Listen UI.
music_analysis_demo
Music analysis demo: onsets + tempo + structure (reference quality).
section18_smoke_dto
Section-18 smoke result as DTO.
shared_clock_demo
Shared media clock + joint window demo.
sonify_ears_demo
U3-style hear: demo events → WAV data URL + optional file under storage.
speech_demo
Greedy phone-decode demo over seed speech weights (not full ASR).
speech_from_disk
Speech using disk weights if present.
synth_with_consent
Reference-tone synth gated on voice consent.