Expose built-in audio utilities as a model family - #534
Merged
Merged
Conversation
cunba-ai
pushed a commit
to cunba-ai/audio.cpp
that referenced
this pull request
Sep 13, 2026
Merge of PR #34 (17 upstream commits, v0.7.4). One conflict in registry.cpp validate_request, resolved as a union of the two path-shape exceptions: fork's empty-path-for-embedded-families skip plus upstream's new builtin_audio_utils utility-id skip (0xShug0#534 exposes denoise/super-resolve incl. all GTCRN variants as a registry family with s2s task; complementary to the fork's CAPI denoise entry, which stays the embedded-asset path). Noted: upstream 0xShug0#530 adds a SECOND C ABI (include/audiocpp.h, src/capi/audiocpp.cpp, target name also 'audiocpp' but under AUDIOCPP_BUILD_C_API, default OFF — mutually exclusive with our AUDIOCPP_BUILD_CAPI at build time; four function names overlap across the two surfaces, harmless per-module but worth remembering). Also brings Kokoro multilingual TTS (GGUF + CPU perf), Moonshine ASR, VibeVoice streaming flash suffix attention + bounded history, Orukeet r3 parakeet variant, pocket-tts reference-audio fix, portable Linux release artifacts, 32-bit overflow fixes, vcvars PATH quote fix. vibevoice embedded-VAD helper intact (option list still honors vibevoice_asr_streaming.vad_model_path), fork_regression 10/10 green, loader catalog in sync, embed intact (~34.9MB .rdata). Generated-by: zcode
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
builtin_audio_utilsmodel family for built-in framework audio utilities.rnnoise,gtcrn, andflashsrinstead of fixed asset paths.docs/audio_tools.md.Validation
Built debug CLI/server and validated CUDA CLI plus
/v1/tasks/runserver requests for:deepfilternet2rnnoisezipenhancergtcrnflashsrThe server responses returned audio payloads, sample rate, channel count, and timing fields for all five utilities.