AI NEWS · 模型情报站发现能力边界,让每一次选择更有依据 ↗基础档案先收录 · 缺失资料持续补齐
THE AI MODEL DIRECTORY 模型探索,从这里开始

找到适合你的 AI 模型。

从语言到影像,从开源到 API。读懂模型能力、比较真实成本,
为你的下一个想法,找到合适的智能引擎。

热门探索
84,115 款模型档案12958 家厂商 / 发布者45 个能力分类464 款有可比报价 · 30 款有公开评测
T文本生成▧图像生成▷视频生成⌘代码生成◖语音合成♫音乐生成⬡3D 建模▤文档分析
DISCOVER & COMPARE

探索 AI 模型 24

为你发现值得关注的模型

d3-coreml

FluidInference

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

分类待补充
输入 待核验→ 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 ↗
来源 / 文档 ↗

kokoro-82m-coreml

FluidInference

Core ML conversions of **hexgrad/Kokoro-82M** (English and Japanese) and **hexgrad/Kokoro-82M-v1.1-zh** (Mandarin). The original Kokoro models and pretrained weights are by hexgrad; this repository provides Apple Core ML conversions and runtime optimizations. See FluidAudio for inference. Available for English, Japanese and Mandarin, with fixed Albert/decoder buckets, native source DSP and a GPU generator adapted from Matt Mireles's conversion. Existing model paths and defaults remain available. Use `KokoroAneManager(version: .v3)` for English, `KokoroAneManager(variant: .japanese, version: .v3)` for Japanese, or `KokoroAneManager(variant: .mandarin, version: .v3)` for Mandarin. All three accept native text and variant voices. Existing callers retain `.legacy`. See SDK usage, voices and platform limits. Requires macOS 15 / iOS 18; physical iOS inference remains unvalidated.

译文排队中 · 当前显示来源原文

输入 文本→ 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 ↗
来源 / 文档 ↗

localvqe-coreml

FluidInference

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

分类待补充
输入 待核验→ 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 ↗
来源 / 文档 ↗

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

分类待补充
输入 待核验→ 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 ↗
来源 / 文档 ↗

NVIDIA's Parakeet-TDT-CTC-110M model converted to CoreML format for efficient inference on Apple Silicon. This is a hybrid ASR model with a shared Conformer encoder and two decoder heads: - **CTC Head**: Fast greedy decoding, ideal for keyword spotting - **TDT Head**: Token-Duration Transducer for high-quality transcription This will: 1. Download the original model from NVIDIA (`nvidia/parakeet-tdt_ctc-110m`) 2. Convert each component to CoreML format 3. Extract vocabulary and create metadata

译文排队中 · 当前显示来源原文

输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

CoreML conversion of nvidia/parakeet-realtime-eou-120m-v1 for streaming speech recognition with end-of-utterance detection on Apple Silicon. Used by FluidAudio for real-time transcription. The RNNT pipeline is split into three CoreML models, exported at two chunk sizes:

译文排队中 · 当前显示来源原文

输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

This is a CoreML-optimized version of NVIDIA's Parakeet TDT 0.6B V2 model, designed for high-performance automatic speech recognition on Apple platforms. Models will continue to evolve as we optimize performance and accuracy. This model has been converted to CoreML format for efficient on-device inference on Apple Silicon and iOS devices, enabling real-time speech recognition with minimal memory footprint. Based on NVIDIA's Parakeet TDT model. CoreML conversion and Swift integration by the FluidInference team.

译文排队中 · 当前显示来源原文

输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

On‑device multilingual ASR model converted to Core ML for Apple platforms. This model powers FluidAudio’s batch ASR and is the same model used in our backend. It supports 25 European languages and is optimized for low‑latency, private, offline transcription. The conversion script is here: https://github.com/FluidInference/mobius/tree/main/models/stt/parakeet-tdt-v3-0.6b/coreml And the benchmarks are here: https://github.com/FluidInference/FluidAudio/blob/main/Documentation/Benchmarks.md#transcription

译文排队中 · 当前显示来源原文

输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

parakeet-ultra-coreml

FluidInference

Core ML build of moondream/parakeet-ultra, a full-precision post-training of `nvidia/parakeet-tdt-0.6b-v3`. Same architecture, 25 languages, tokenizer and output conventions as v3; drop-in for the v3 component contract. Encoder is int8 linear per-channel (595 MB); decoder and joint are re-exported from the Ultra checkpoint; preprocessor and vocabulary are the v3 ones. Ultra wins all 24 FLEURS languages. The int8 encoder scores the same WER as an fp16 export (2.13 % / 3.79 %). Speed is within a few percent of v3 run back to back on the same machine (test-clean 126.7× vs 128.6× on the ANE). Conversion recipe: FluidInference/mobius `models/stt/parakeet-ultra/coreml`. License CC-BY-4.0, as the upstream checkpoint.

译文排队中 · 当前显示来源原文

输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

phonon-2-coreml

FluidInference

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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

silero-vad-coreml

FluidInference

A CoreML implementation of the Silero Voice Activity Detection (VAD) model, optimized for Apple platforms (iOS/macOS). This repository contains pre-converted CoreML models ready for use in Swift applications. This is how the model performs against the silero-vad v6.0.0 basline Pytorch JIT version Note that we tested the quantized versions, as the model is already tiny, theres no performance imporvement at all.

译文排队中 · 当前显示来源原文

分类待补充
输入 待核验→ 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 ↗
来源 / 文档 ↗

Core ML conversions used by FluidAudio for on-device speaker diarization on Apple platforms. The supported Community-1 artifact set is distributed under CC-BY-4.0. See NOTICE.md for attribution and the precise license scope, and PROVENANCE.md plus provenance.json for source, conversion, environment, and file-integrity records. The snapshot includes uncompiled packages for `Segmentation`, `FBank`, `Embedding`, and `PldaRho` under `mlpackages/`; no uncompiled `PLDA` package was published. These are Core ML conversions, not fine-tuned models.

译文排队中 · 当前显示来源原文

分类待补充
输入 待核验→ 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 ↗
来源 / 文档 ↗
COST EXPLORER

好模型,也要算好成本。

费用分析

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

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

选型与常见问题
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。

AI NEWS · 从信息到选择

资讯看趋势,工具提效率,模型筑可能。

探索 AI 资讯 ↗发现 AI 工具 ↗