voxlock
arbazsiddiqui基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 342
Please note that this model is for research purpose only. A commercial license for a model that has been trained on much more data can be acquired with audEERING. The model expects a raw audio signal as input, and outputs predictions for arousal, dominance and valence in a range of approximately 0...1. In addition, it provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust on MSP-Podcast (v1.7). The model was pruned from 24 to 12 transformer layers before fine-tuning. An ONNX export of the model is available from doi:10.5281/zenodo.6221127. Further details are given in the associated paper and tutorial.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust on aGender, Mozilla Common Voice, Timit and Voxceleb 2. For this version of the model we only trained the first six transformer layers. An ONNX export of the model is available from doi:10.5281/zenodo.7761387. Further details are given in the associated paper and tutorial.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗RE-USE-GGUF
audio-cppGGUF 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.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SAM-Audio-GGUF
audio-cppGGUF 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.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DeepFilterNet3-CoreML
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗PersonaPlex-7B-MLX-4bit
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Pyannote-Community-1-CoreML
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Qwen3-ForcedAligner-0.6B-4bit
aufklarerPredicts **word-level timestamps** for audio+text pairs in a single non-autoregressive forward pass. Unlike ASR (autoregressive, token-by-token), the forced aligner runs the **entire sequence in one forward pass** through the decoder. The classify head predicts a timestamp class (0–4999) at each ` ` token position, which maps to time via `class_index × 80ms`. Text decoder (attention projections, MLP, embeddings) quantized to 4-bit using group quantization (group_size=64). Audio encoder and classify head kept as float16 for accuracy.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Sidon-CoreML
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Silero-VAD-v6.2.1-MLX
aufklarerMeasured with `speech-swift` release tests on Apple Silicon using a 20 s 16 kHz speech fixture, 625 streaming chunks. The exported safetensors were also checked tensor-by-tensor against the upstream v6.2.1 JIT state dict after conversion; the maximum absolute tensor difference was 0.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Smart-Turn-v3.2-CoreML
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VoiceChat-11B-Perception-MLX-int5
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗WeSpeaker-ResNet34-LM-CoreML
aufklarer基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗WeSpeaker-ResNet34-LM-MLX
aufklarerMLX-compatible weights for WeSpeaker ResNet34-LM, converted from the pyannote speaker embedding model with BatchNorm fused into Conv2d. WeSpeaker ResNet34-LM is a speaker embedding model (~6.6M params) that produces 256-dimensional L2-normalized speaker embeddings from audio. Trained on VoxCeleb for speaker verification and diarization. Converts the original pyannote/wespeaker-voxceleb-resnet34-LM checkpoint using a custom unpickler (no pyannote.audio dependency required). Key transformations:
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗matpac_music
auriankelen基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-alpha-120s
awsaf49SONICS: Synthetic Or Not - Identifying Counterfeit Songs ICLR 2025 [Poster] The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction. - 📄 **Paper** - 🎵 **Dataset** - 🔬 **ArXiv** - 💻 **GitHub**
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-alpha-5s
awsaf49The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction. .hf-button { display: inline-flex; align-items: center; gap: 6px; padding: 6px 12px; font-size: 14px; font-weight: bold; color: white; border-radius: 6px; text-decoration: none; } .hf-button img { height: 18px; }
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-beta-120s
awsaf49The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction. .hf-button { display: inline-flex; align-items: center; gap: 6px; padding: 6px 12px; font-size: 14px; font-weight: bold; color: white; border-radius: 6px; text-decoration: none; } .hf-button img { height: 18px; }
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-beta-5s
awsaf49基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-gamma-120s
awsaf49The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction. .hf-button { display: inline-flex; align-items: center; gap: 6px; padding: 6px 12px; font-size: 14px; font-weight: bold; color: white; border-radius: 6px; text-decoration: none; } .hf-button img { height: 18px; }
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonics-spectttra-gamma-5s
awsaf49The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction. .hf-button { display: inline-flex; align-items: center; gap: 6px; padding: 6px 12px; font-size: 14px; font-weight: bold; color: white; border-radius: 6px; text-decoration: none; } .hf-button img { height: 18px; }
译文排队中 · 当前显示来源原文
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗distil-ast-audioset
bookbot基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。