audio.cpp

audio-cpp's activity

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

New activity in BreezeBlue/Breeze-TTS-2 1 day ago

Breeze TTS 2 is available in audio.cpp release 0.7.2. 6GB VRAM 4x faster than realtime. No Python. Demo included

🚀 4

5

#5 opened 9 days ago by

audio-cpp

New activity in BreezeBlue/Breeze-TTS-2 5 days ago

Breeze-TTS-2 license concern: GGUF distribution requires user acceptance

1

#9 opened 5 days ago by

audio-cpp

New activity in audio-cpp/audio.cpp-gguf 5 days ago

Request mirroring to ModelScope

2

#3 opened 16 days ago by

LaikaFramework

New activity in ibm-granite/granite-speech-5.0-470m-turboctc-nc 6 days ago

[audio.cpp] Granite-speech-5.0-470m-turboctc-nc was included in audio.cpp release 0.7

👍 1

#9 opened 6 days ago by

audio-cpp

New activity in audio-cpp/audio.cpp-gguf 8 days ago

No Vibevoice 7B ggufs?

4

#4 opened 9 days ago by

detemasinton

Fish Audio custom quants

1

#2 opened 29 days ago by

nikich340

New activity in FireRedTeam/FireRedTTS3 9 days ago

[Demo included] audio.cpp supports FireRedTTS3 in release 0.7! 4x faster than realtime. No Python. Support Vulkan/Metal/AMD

🔥 1

#6 opened 9 days ago by

audio-cpp

New activity in MiniMaxAI/MiniMax-Music3 16 days ago

Audio.cpp now supports MiniMax-Music3. No Python. Demo and performance metrics inside.

2

#24 opened 17 days ago by

audio-cpp

New activity in IndexTeam/IndexTTS-2.5 17 days ago

Audio.cpp now supports IndexTTS-2.5. No Python. CUDA/Vulkan/Metal/HIP (and even Orin). Up to 8.5× realtime on RTX5090.

👍 1

#2 opened 17 days ago by

audio-cpp

New activity in audio-cpp/audio.cpp-gguf 28 days ago

OmniVoice quantization question

1

#1 opened about 1 month ago by

nikich340

New activity in Audio8/Audio8-TTS-Preview-0.6b 30 days ago

We use Fishaudio already and are curious about this

4

#6 opened about 1 month ago by

YellowjacketGames

New activity in microsoft/VibeVoice-1.5B about 1 month 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 about 1 month ago by

audio-cpp

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 2 months ago by

audio-cpp

New activity in bosonai/higgs-tts-3-4b about 1 month ago

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

🔥 2

3

#24 opened about 1 month ago by

audio-cpp

New activity in fishaudio/s2-pro about 1 month ago

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

🚀 1

1

#27 opened about 1 month ago by

audio-cpp

New activity in mistralai/Voxtral-Mini-4B-Realtime-2602 about 2 months 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 about 2 months ago by

audio-cpp

New activity in nvidia/nemotron-3.5-asr-streaming-0.6b about 2 months ago

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

🔥 3

2

#24 opened about 2 months ago by

audio-cpp