Chatterbox-Multilingual-MLX-fp16
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。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 33
CosyVoice3-0.5B-MLX-bf16
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。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗CSM-1B-MLX-5bit
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。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Audio→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Kokoro-82M-CoreML
aufklarerEnd-to-end CoreML export of hexgrad/Kokoro-82M at FP16, optimized for Apple Neural Engine. Requires iOS 18+ / macOS 15+. A single `kokoro_5s.mlmodelc` runs the full pipeline (BERT → duration prediction → fixed-shape alignment → prosody → decoder) in one CoreML call. G2P (grapheme-to-phoneme) is a separate pair of CoreML models. Looking for a smaller variant? See `aufklarer/Kokoro-82M-CoreML-INT8` — INT8 k-means palettized, 83 MB vs 325 MB here, with log-spec distance 0.42 vs this FP16 reference on a validation utterance.
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Parakeet-EOU-120M-CoreML-INT8
aufklarerStreaming speech recognition with end-of-utterance detection, converted to CoreML for Apple Neural Engine inference. Part of speech-swift — on-device speech AI for Apple Silicon. Based on nvidia/parakeet_realtime_eou_120m-v1 (FastConformer-RNNT, cache-aware streaming). Converted from nvidia/parakeet_realtime_eou_120m-v1 using coremltools 8.3 with INT8 palettization.
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Parakeet-TDT-v3-CoreML-INT8
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。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Parakeet-TDT-v3-CoreML-INT8-30s
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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Parakeet-TDT-v3-CoreML-INT8-iOS-5s
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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Basic profile indexed · More details to follow
Input Audio→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Audio→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Pyannote-Segmentation-MLX
aufklarerMLX-compatible weights for pyannote/segmentation-3.0 (PyanNet), converted from the official PyTorch Lightning checkpoint with pre-computed SincNet filters. PyanNet is a speaker segmentation model (~1.5M params) that processes 10-second audio windows and outputs 7-class powerset probabilities for up to 3 simultaneous speakers. Used for both voice activity detection (binary) and speaker diarization (per-speaker). Converts the gated pyannote/segmentation-3.0 checkpoint using a custom unpickler (no pyannote.audio dependency required). Key transformations:
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-0.6B-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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-0.6B-MLX-8bit
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。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-1.7B-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。
Basic profile indexed · More details to follow
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-1.7B-MLX-5bit
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。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-1.7B-MLX-8bit
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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-ASR-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。
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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.
Input Audio→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Basic profile indexed · More details to follow
Input Audio→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Silero-VAD-v5-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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Silero-VAD-v5-MLX
aufklarerMLX-compatible weights for Silero VAD v5, converted from the official JIT model. Silero VAD v5 is a lightweight (~309K params) voice activity detection model that processes 512-sample chunks (32ms @ 16kHz) with sub-millisecond latency. It outputs a speech probability between 0 and 1 for each chunk, with LSTM state carried across chunks for streaming operation. **Architecture:** STFT → 4×Conv1d+ReLU encoder → LSTM(128) → Conv1d decoder → sigmoid
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.