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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗DISCOVER & COMPARE
AIモデルを探す 341
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.
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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.
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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.
翻訳待ち・原文を表示
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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.
翻訳待ち・原文を表示
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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.
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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.
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 音声
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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:
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗sonics-spectttra-alpha-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; }
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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; }
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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; }
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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; }
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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; }
翻訳待ち・原文を表示
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗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。
基本情報を収録・詳細は順次追加
入力 音声→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗該当するモデルがありません
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
COST EXPLORER
モデル選びに、費用の視点も。
月間トークン数を調整してAPI費用を比較。
1 M = 100万トークン・米ドル
同一チャネルの基本テキスト料金を比較
同一チャネルの基本テキスト料金を比較
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
MODEL HANDBOOK
モデルを理解して選ぶ
API料金はどう比較しますか？+
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
オープンウェイトは無料で商用利用できますか？+
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
ランキング1位が最適ですか？+
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。