Skip to content

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.

active 2026-06-252026-08-10 (UTC)

Partial coverage11,603 / 12,736 hourly files (91%) · 2 absent upstream · 1,129 failed, retryable2025-02-262026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
93
Pushes
55
Pull requests
1
Issues
2
Stars
14
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 47 days from 2026-06-25 to 2026-08-10. Pushes: 55 total, peak 5 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 2 total, peak 1 in a day. Comments: 8 total, peak 2 in a day. Stars: 14 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
0xShug0595504
bakamomi2000
justinjohn03062011
xashr1001
mirek1901001
datkun92-code1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#192datkun92-code2026-08-07 17:07
    Vulkan: q8_0 Irodori-TTS output saturates to +32767 on AMD RX 6800; disabling integer dot avoids it
  • Issue comment#1850xShug02026-08-07 16:56
    WebUI - Initial native Svelte WebUI embedded inside audiocpp_server.exe — no Python, Node.js, or Gradio needed
  • Issue comment#101mirek1902026-07-26 11:17
    Extremely long first CUDA graph warm-up (~99s) before first TTS request on RTX 5070 Ti (Windows 11)
  • Issue comment#84xashr2026-07-23 16:51
    Support all CPU variants with portable Docker builds
  • Issue comment#630xShug02026-07-16 00:41
    TTS OutieTTS 1.0 + cloning audio
  • Issue comment#270xShug02026-07-05 00:49
    Memory leak
  • Issue#27bakamomi2026-07-05 00:04
    Memory leak
  • Issue comment#270xShug02026-07-04 23:17
    Memory leak
  • Issue#28bakamomi2026-07-04 21:22
    [Question] Higgs TTS v3 support
  • Issue comment#19justinjohn03062026-07-02 16:24
    Add MOSS-TTS-Local model family (+ VibeVoice 7B / fine-tune adapters)
  • Pull request#19justinjohn03062026-07-02 05:22

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 14 stars here means stars gained during the window, not the repo's star count.