audio.cpp

audio-cpp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 1 day ago

audio-cpp/audio.cpp-gguf

Text-to-Speech • 0.2B • Updated 1 day ago • 156k • 51

New activity in audio-cpp/audio.cpp-gguf 6 days ago

Fish Audio custom quants

1

#2 opened 6 days ago by

nikich340

OmniVoice quantization question

1

#1 opened 10 days ago by

nikich340

New activity in Audio8/Audio8-TTS-Preview-0.6b 7 days ago

We use Fishaudio already and are curious about this

3

#6 opened 10 days ago by

YellowjacketGames

New activity in microsoft/VibeVoice-1.5B 9 days ago

[audio.cpp] C++/GGML VibeVoice 1.5B/7B/LORA: 93.9-minute podcast in 18.2 mins (10 steps, No quantization) 5.15x faster than real time.

#53 opened 9 days ago by

audio-cpp

New activity in nvidia/nemotron-3.5-asr-streaming-0.6b 10 days ago

Nemotron 3.5 ASR Streaming 0.6b in native C++/GGML. RTF = 0.0066 on RTX 5090

🔥 3

2

#24 opened about 1 month ago by

audio-cpp

updated a model 18 days ago

mistral-experimental/AudioCPP-Voxtral-Mini-4B-Realtime-2602-GGUF

Automatic Speech Recognition • Updated 16 days ago • 1.7k • 4

published a model 18 days ago

mistral-experimental/AudioCPP-Voxtral-Mini-4B-Realtime-2602-GGUF

Automatic Speech Recognition • Updated 16 days ago • 1.7k • 4

New activity in bosonai/higgs-tts-3-4b 20 days ago

Portable C++/GGML implementation of Higgs Audio v3 TTS: 8.8–10.1× real-time (warmed) and 8.5× real-time (longform)

🔥 2

2

#24 opened 22 days ago by

audio-cpp

New activity in fishaudio/s2-pro 22 days ago

Portable C++/GGML implementation of Fish Audio S2 Pro. 3x faster than real time.

1

#27 opened 22 days ago by

audio-cpp

New activity in mistralai/Voxtral-Mini-4B-Realtime-2602 26 days ago

[audio.cpp] C++/GGML based Voxtral Mini 4B Realtime impl. 16.39x (0.0610 RTF) realtime offline, 170ms TTFT streaming on RTX 5090

🔥❤️ 1

#48 opened 26 days ago by

audio-cpp

published a model about 1 month ago

audio-cpp/audio.cpp-gguf

Text-to-Speech • 0.2B • Updated 1 day ago • 156k • 51

New activity in nvidia/nemotron-3.5-asr-streaming-0.6b about 1 month ago

Nemotron 3.5 ASR Streaming 0.6b in native C++/GGML. RTF = 0.0066 on RTX 5090

🔥 3

2

#24 opened about 1 month ago by

audio-cpp