audio.cpp

In plain words: Engine: audio.cpp

Designed 1 min read 3 glossary terms 6 connected pages
The short version written for the Snayu team

Short candidate page for using audio.cpp as a local engine for music, source separation and speech, with output meaning owned by Voice (Echo), the music app or another owner.

Why read it: Read this when evaluating local audio inference options.
  1. 1Pin runtime revision, model family, worker shape and devices before admitting it.
  2. 2If no managed lifecycle is needed, use a bounded tool profile instead of a local service.
  3. 3Model weights and licences are separate facts from the Apache-2.0 runtime licence.

Designed Candidate study only.

Words on this page, decoded click one for its card

The original text Underlined words open their plain-English card.

Consider audio.cpp when a bounded local audio operation needs an inference engine. A pinned server or worker may justify a SoulstoneLocal Model and local AnimatorModel Runtime. The meaning of its output still belongs to the consuming owner: EchoVoice for speech mechanics, Riffmaw for music, or another application according to the admitted operation and semantic role.

The candidate study concerns music, separation, and speech families supported by an exact pinned runtime profile; it does not admit arbitrary model execution merely because the runtime is Apache-2.0. Model weights, dependencies, family support, input/output bytes, and license terms remain separate profile facts.

To admit an audio.cpp SoulstoneLocal Model, first pin how it will run: runtime revision, model family, worker or server shape, queue and lifecycle behavior, and device topology. Then establish the audio formats, cancellation boundary, output custody, and measured receipt. If a library or one-shot CLI needs no independently managed lifecycle, keep it in a bounded ToolProfile instead.

The music candidate is recorded in Riffmaw Studio; speech law and Language Edition's use of exact STT/TTS operations remain in the Audio covenant and Language Edition. Audio admission remains separate from the generic SoulstoneLocal Model engine catalog.

See audio.cpp and the owning Echo, Riffmaw, and role-specific application contracts.