Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
feiyunwill
/
audio.cpp
Public
forked from
0xShug0/audio.cpp
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Breadcrumbs
History for
audio.cpp
include
on
main
User selector
All users
Datepicker
All time
Commit history
Commits on Oct 4, 2026
feat: add lfm2_audio TTS for LFM2.5-Audio EN and JP (#768)
Show description for 42faa8b
ykhrustalev
authored
42faa8b
View commit details
Copy full SHA for 42faa8b
View code at this point
Browse repository at this point
Add Kittentts2 community model (#776)
Show description for d3ab9df
dignome
authored
d3ab9df
View commit details
Copy full SHA for d3ab9df
View code at this point
Browse repository at this point
server: separate legacy and experimental parallel jobs runtimes (#715)
Show description for e3e1bc7
mirek190
authored
e3e1bc7
View commit details
Copy full SHA for e3e1bc7
View code at this point
Browse repository at this point
Commits on Oct 3, 2026
Add OWSM v4 and OWSM-CTC v4 (#774)
Show description for 2ba9fa8
0xShug0
authored
2ba9fa8
View commit details
Copy full SHA for 2ba9fa8
View code at this point
Browse repository at this point
perf(lfm2_audio): keep the encoder graph and its compute buffer between chunks (#766)
Show description for 2892ed3
ykhrustalev
authored
2892ed3
View commit details
Copy full SHA for 2892ed3
View code at this point
Browse repository at this point
Commits on Oct 2, 2026
Add Audio Flamingo 3 and Next support (#763)
Show description for a83d302
0xShug0
authored
a83d302
View commit details
Copy full SHA for a83d302
View code at this point
Browse repository at this point
Add CrisperWhisper 2.0 with long-form transcription and alignment
0xShug0
committed
f9228b6
View commit details
Copy full SHA for f9228b6
View code at this point
Browse repository at this point
feat: add lfm2_audio ASR for LFM2.5-Audio EN and JP (#758)
Show description for eebc4b3
ykhrustalev
authored
eebc4b3
View commit details
Copy full SHA for eebc4b3
View code at this point
Browse repository at this point
fix(torch_bin): honour _rebuild_tensor_v2 storage_offset and reject non-contiguous tensors (#757)
Show description for 2d600d9
Zhuoxi2000
authored
2d600d9
View commit details
Copy full SHA for 2d600d9
View code at this point
Browse repository at this point
Commits on Oct 1, 2026
Add Index-Echo S2TT translation models (#755)
0xShug0
authored
76e26b8
View commit details
Copy full SHA for 76e26b8
View code at this point
Browse repository at this point
Add KugelAudio native TTS with batched CFG and streaming (#744)
0xShug0
authored
7c2ec18
View commit details
Copy full SHA for 7c2ec18
View code at this point
Browse repository at this point
refactor(reuse): move frontend header under include
0xShug0
committed
f54ec43
View commit details
Copy full SHA for f54ec43
View code at this point
Browse repository at this point
Add Smart Turn v3.2 offline turn detection (#743)
0xShug0
authored
8ebcc04
View commit details
Copy full SHA for 8ebcc04
View code at this point
Browse repository at this point
Add Sidon speech restoration model support (#742)
0xShug0
authored
a83ed6a
View commit details
Copy full SHA for a83ed6a
View code at this point
Browse repository at this point
Commits on Sep 30, 2026
Add RE-USE audio restoration and native task batching (#714)
0xShug0
authored
947ca1f
View commit details
Copy full SHA for 947ca1f
View code at this point
Browse repository at this point
Add opt-in SSM and projection support for CUDA and Vulkan (#713)
0xShug0
authored
43fd790
View commit details
Copy full SHA for 43fd790
View code at this point
Browse repository at this point
Commits on Sep 29, 2026
Organize framework components by responsibility (#734)
0xShug0
authored
ed96b73
View commit details
Copy full SHA for ed96b73
View code at this point
Browse repository at this point
Echo-TTS VRAM improvements (#731)
Show description for 0bc3364
lojack5
authored
0bc3364
View commit details
Copy full SHA for 0bc3364
View code at this point
Browse repository at this point
Commits on Sep 28, 2026
Make model-local component architecture names explicit (3) (#729)
Show description for f825d1d
0xShug0
authored
f825d1d
View commit details
Copy full SHA for f825d1d
View code at this point
Browse repository at this point
Make remaining model component names architecture-explicit (#728)
0xShug0
authored
901f9ed
View commit details
Copy full SHA for 901f9ed
View code at this point
Browse repository at this point
Make model-local component architecture names explicit (1) (#727)
0xShug0
authored
1716940
View commit details
Copy full SHA for 1716940
View code at this point
Browse repository at this point
Clarify shared decoder and model architecture names (#725)
0xShug0
authored
eea15b3
View commit details
Copy full SHA for eea15b3
View code at this point
Browse repository at this point
Rename shared HuBERT encoder as Wav2Vec2 runtime (#724)
0xShug0
authored
342d26d
View commit details
Copy full SHA for 342d26d
View code at this point
Browse repository at this point
Add standalone Tone Color VC model support (#716)
Show description for f99bd1e
0xShug0
authored
f99bd1e
View commit details
Copy full SHA for f99bd1e
View code at this point
Browse repository at this point
Commits on Sep 27, 2026
Add native SAM Audio separation (#711)
Show description for 90c56c2
0xShug0
authored
90c56c2
View commit details
Copy full SHA for 90c56c2
View code at this point
Browse repository at this point
Commits on Sep 26, 2026
Add native SAMSONE audio understanding (#709)
Show description for 7b1cd06
0xShug0
authored
7b1cd06
View commit details
Copy full SHA for 7b1cd06
View code at this point
Browse repository at this point
Add GigaAM v3 and multilingual ASR support (#708)
0xShug0
authored
f71fcd8
View commit details
Copy full SHA for f71fcd8
View code at this point
Browse repository at this point
Add optimized Maya1 TTS support (#707)
0xShug0
authored
ac435fb
View commit details
Copy full SHA for ac435fb
View code at this point
Browse repository at this point
Add HTDemucs 6-stem source separation (drums, bass, vocals, other, guitar, piano) (#694)
Show description for 94bd465
SMGoro
and
root
authored
94bd465
View commit details
Copy full SHA for 94bd465
View code at this point
Browse repository at this point
Add speaker-tagged transcription to Nemotron ASR (#681)
Show description for da18f6d
LysanderdeJong
authored
da18f6d
View commit details
Copy full SHA for da18f6d
View code at this point
Browse repository at this point
confucius4_r2t2: make streaming chunks incremental instead of O(utterance) (#696)
Show description for e9516ed
scriptease
and
claude
authored
e9516ed
View commit details
Copy full SHA for e9516ed
View code at this point
Browse repository at this point
Commits on Sep 25, 2026
nemotron_3_diar: write speaker probabilities as safetensors (#686)
Show description for e79205f
LysanderdeJong
authored
e79205f
View commit details
Copy full SHA for e79205f
View code at this point
Browse repository at this point
nemotron_asr: move options to the model spec (#685)
Show description for 7c79c9a
LysanderdeJong
authored
7c79c9a
View commit details
Copy full SHA for 7c79c9a
View code at this point
Browse repository at this point
metrics: process peak memory in --metrics, reserved-vs-used per ggml context in --log (#688)
Show description for 1bfb9c5
engival
authored
1bfb9c5
View commit details
Copy full SHA for 1bfb9c5
View code at this point
Browse repository at this point
moss_ttsd: hold the encoder at its stored type and widen to f32 in the graph (#690)
Show description for 14590e5
christopherthompson81
authored
14590e5
View commit details
Copy full SHA for 14590e5
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.
