This directory contains audio.cpp-native GGUF conversions of multiple speech models. These files are intended for use with audio.cpp. For conversion details, supported layouts, direct-file loading, sidecar embedding, and the latest compatibility notes, see the audio.cpp GGUF guide: The table lists the GGUF packages currently provided by this repository. License names follow audio.cpp's model license reference, which also records commercial-use conditions and other important notes.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
These self-contained GGUFs package the model tensors, tokenizer, configuration, and audio.cpp model spec for Audio Flamingo 3, Audio Flamingo Next, and Music Flamingo. AF3 and Next support transcription, captioning, and questions about speech, music, and environmental sounds. Music Flamingo specializes in music understanding; it produces text, not audio. Select a GGUF with `--model`. Use a question such as `Describe the instruments and tempo.` for general audio understanding. Requested timestamps or speaker descriptions are generated text, not structured alignment or diarization results. For server use, configure family `audio_flamingo`, task `asr`, and mode `offline`, then submit audio to `/v1/audio/transcriptions` with the instruction in `prompt`.
翻訳待ち・原文を表示
入力 音声→ 出力 テキスト
These GGUF files are for use with audio.cpp. The card's `base_model` points to the Tencent AuK base model. This package also includes optional files converted from AuK-Flash; Flash is a separate distilled variant and is not the pinned base model. > **Output quality:** We validate parity with upstream Python for the tested configuration, not whether AuK's output meets every quality expectation. If a result is disappointing, listen to the corresponding Python reference WAV linked below first. A similar Python result points to the upstream model's behavior, not necessarily an audio.cpp conversion issue. The quantized component combinations have not received the same 16-task parity validation. Pass the downloaded directory to `audiocpp_cli --model`. Keep the `config/` and `tokenizer/` directories alongside the GGUF files. The default components are `auk-base-f32.gguf`, `qwen2.5-omni-3b-bf16.gguf`, and `auk-vae-f32.gguf`. AuK-Flash requires `--session-option auk.variant=flash`; its default generator is `auk-flash-f32.gguf`. The Qwen component is Qwen2.5-Omni-3B.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
GGUF packages for native speech-to-text translation with audio.cpp. Chinese speech produces timestamped source transcripts and English, Spanish, or Japanese translations. This port supports **S2TT only**; it does not generate translated speech. **There is room to improve 9B output parity and quantized quality**. Focused PRs with reproducible C++/Python comparisons are welcome. Note that 2B and 9B use the same C++ translation path, including the prompt, audio encoder, decoder implementation, and greedy sampler. 2B orig is parity safe, while 9B orig has drifts. 2B has 24 layers and tied token/output embeddings; 9B has 32 layers and a separate LM head. That can change how sensitive their outputs are to numerical differences, but I have not proved that it explains the 9B mismatch. These files were converted from the official 2B checkpoint at `72fd8bdc9bf8251f1c35f6d6289a950eda154395` and 9B checkpoint at `05f86cb7a38684916e193282b6cc02462ace4043`. Each GGUF embeds the audio tower, connector, text decoder, tokenizer, configuration, and audio.cpp model spec. The unused vision weights are not included.
翻訳待ち・原文を表示
入力 音声→ 出力 テキスト
Use this package with audio.cpp. It synchronizes lip motion in an existing video with supplied speech. > [!WARNING] > This package contains InsightFace face detection and landmark > weights restricted to non-commercial research. LatentSync's Apache-2.0 license > does not override those terms. Review upstream licenses before redistribution > or deployment. Each GGUF includes the temporal diffusion U-Net, Whisper Tiny audio encoder, SD VAE, SCRFD face detector, 106-point landmark model, face mask, configuration sidecars, and embedded audio.cpp model spec. Inference requires no Python or ONNX Runtime.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
Native GGUF package of Wan-AI/Wan2.2-S2V-14B with the official Quark-Vision/Live-Avatar LoRA merged for audio.cpp. LiveAvatar generates an audio-driven avatar video from a reference image, speech audio, and a text description. LiveAvatar can keep the denoiser transformer blocks in pinned host memory and stage one layer group at a time. This makes 720p generation possible near a 16 GiB VRAM limit, at the cost of additional host-to-device transfers. The validated 1280x720 run generated 93 frames at 16 FPS (5.81 seconds of video) in **276 seconds wall time** (4 minutes 36 seconds) and peaked at **15,993 MiB VRAM** on an RTX 5090.
翻訳待ち・原文を表示
入力 画像→ 出力 動画
GGUF conversion of inclusionAI/Ming-3.0-audio-tiny, pinned to revision `25b96e30be3739849bf76c0f48ac11db4a262fb3`. Upstream code: Ming-3.0-audio-flash. The single GGUF contains the audio encoder, KDA/MLA MoE Thinker, Talker, audio VAE, CAMPPlus speaker encoder, tokenizers, and configuration. It supports offline transcription, audio understanding, named voices, voice cloning, and spoken responses. Speech output is mono 44.1 kHz. Both quantized packages preserve the audio encoder, Thinker attention and MLP projections, Talker, VAE and speaker encoder. TTS-only memory usage therefore does not shrink with Thinker expert quantization.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
Star or watch audio.cpp on GitHub to follow model integration, merged code changes and inference improvements. GGUF packages of Ming 3.0 TTS 0.5B for audio.cpp. Each file contains the Qwen backbone, flow-matching head, audio VAE, CAMPPlus speaker encoder, configuration, tokenizer and model spec. Output is mono at 44.1 kHz. No separate codec or Python runtime is required. Upstream implementation: inclusionAI/Ming-3.0-tts, pinned to revision `e999c39fa676722aaa9ea29b5aa19a90525b271f` for the Python comparison.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
Star our repo so you don't miss important updates! https://github.com/0xShug0/audio.cpp Upstream model: https://huggingface.co/MiniMaxAI/MiniMax-Music3 Upstream license: https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/LICENSE - The implementation is available on the `main` branch and release 0.6.1. - The current runtime uses model-local resource loading instead of treating the v1 spec as the runtime contract. This keeps component selection flexible while the package layout and option surface settle. - The default component mix favors Q4_0 for the large language model and flow transformer, with Q8_0 for the RVQ depth decoder. - BF16, Q8_0, and Q4_0 component variants are included for quality/performance comparison. - Longer generations such as five-minute songs are supported as long-form runs, but they are currently tuned for completion and quality checks rather than realtime throughput. - Memory usage remains an active optimization target for larger durations and alternate component mixes.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
**Update 2026-09-26**: Since the initial release, Nemotron 3 Diarization has received improved NeMo parity for ragged batches and streaming tails, selectable flash/eager attention, self-describing speaker-probability output, ASR-compatible latency profiles, and integration with Nemotron’s speaker-tagged transcription pipeline. Existing published GGUFs remain compatible. GGUF weights for native inference with audio.cpp. Tested on CUDA, Vulkan, and Metal(Mac) backends. Nemotron 3 Diarization identifies who spoke when, with up to eight speakers. It supports offline, streaming, and server batch diarization. It returns speaker turns and timestamps, not transcribed words. This package was converted from the original `.nemo` checkpoint, not from an existing GGUF. Each file contains 362 tensors, frontend configuration, and an embedded model spec, with no separate weight or configuration files required. The BF16 file retains the original model weight precision, with the frontend mel filter stored in F32. BF16 is parity safe with Nemo with TF32 control.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
GGUF weights for native inference with audio.cpp. RE-USE restores degraded speech while preserving its input sample rate. It uses a convolutional encoder/decoder and 30 bidirectional time-frequency Mamba blocks. The checkpoint and reference implementation are pinned to nvidia/RE-USE, revision 022e920d727347a64d6c21fbf0628f2a5f37ad78. Each GGUF includes the model weights, configuration, and audio.cpp model spec. No separate encoder or tokenizer is required. Packages are converted directly from the original safetensors, not from another GGUF. Only F32 is provided. F16 and Q8 were rejected because their small disk savings did not improve speed or peak VRAM in testing, while introducing waveform drift and additional packaging complexity.
翻訳待ち・原文を表示
入力 音声→ 出力 音声
GGUF weights for native inference with audio.cpp. SAM Audio separates a sound described by text, a masked image or video, or positive and negative time spans from an input recording. These packages use the original Meta checkpoints, not the separate `-tv` variants. The official SAM Audio implementation is pinned to bb4c699.
翻訳待ち・原文を表示
入力 音声→ 出力 音声
GGUF conversion of m-a-p/SheetSage2 for audio.cpp. SheetSage2 transcribes music into melody, chords, beats, key, structure, and editable scores. This is a converted checkpoint, not a new model or an official upstream release. - SheetSage2: pinned revision eab522a8168e8b8b8c4856bf8609cd86198f01fe. - Backbone: m-a-p/MERT-v2-FullSong. - SheetSage2 source safetensors SHA256: `b235f68091a5f5b644000f2b5acb57d1e70432aca2b34ab1b9cf27236e1f4274`. - Backbone source safetensors SHA256: `e6dd2ab187d6dd62b6521cd7d8f932e237acf0c5757745a7232082e28391350d`. The packaged file uses the audio.cpp SheetSage2 runtime, not the upstream Transformers loader.
翻訳待ち・原文を表示
入力 テキスト→ 出力 埋め込み
GGUF conversion of vibevoice/VibeVoice-7B for audio.cpp. Upstream model: vibevoice/VibeVoice-7B - `vibevoice-7b-q8_0.gguf`: Q8_0 GGUF package for VibeVoice 7B. - `LICENSE`: MIT license from the upstream VibeVoice project.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
This repository contains audio.cpp-native GGUF builds of `microsoft/VibeVoice-ASR-Streaming-7B`. Each GGUF is self-contained and embeds the audio.cpp package spec and required sidecars. - Upstream repository: https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B - Pinned upstream revision: `60d858b518b4e19d404af3737f848fc185b30177` - Upstream license: MIT
翻訳待ち・原文を表示
入力 音声→ 出力 テキスト
This repository contains audio.cpp-native GGUF weights for Yue2-3B. The model has been merged into the main branch. The demos below were generated with `yue2-3b-bf16.gguf` and `yue2-vae-f32.gguf`. The `_q8.wav` comparison files were generated with `yue2-3b-q8_0.gguf` and `yue2-vae-f16.gguf` using the same prompts and seeds. The `_q4_0.wav` comparison files were generated with `yue2-3b-q4_0.gguf` and `yue2-vae-f16.gguf`. Replace ` ` with your audio.cpp checkout and ` ` with this downloaded GGUF repo directory. To generate the Q4_0 versions, use the same commands and replace `--session-option yue2.model_gguf=yue2-3b-bf16.gguf` with `--session-option yue2.model_gguf=yue2-3b-q4_0.gguf`, and use `--session-option yue2.vae_gguf=yue2-vae-f16.gguf`. Measured with audio.cpp server mode on an RTX 5090, using the official `tonight-awake` longform example. Each run restarted the server and used one short warmup request before the measured longform request. Peak VRAM was sampled continuously during the measured request.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
